remove hf

configuration_prismatic.py

@@ -1,156 +0,0 @@
-"""
-configuration_prismatic.py
-
-HuggingFace-style configuration definition for Prismatic VLMs, inheriting from `transformers.PretrainedConfig`.
-Default configuration specifies `siglip-224px+7b`.
-"""
-
-from typing import Any, Dict, List, Optional
-
-from transformers import PretrainedConfig
-from transformers.models.auto import CONFIG_MAPPING
-
-# === Utilities for Mapping Prismatic names to HF names ===
-# fmt: off
-VISION_BACKBONE_TO_RESOLUTION: Dict[str, List[int]] = {
-    "clip-vit-l": [224], "siglip-vit-so400m": [224], "dinov2-vit-l": [224], "in1k-vit-l": [224],
-
-    "clip-vit-l-336px": [336],
-    "siglip-vit-so400m-384px": [384],
-
-    "dinoclip-vit-l-336px": [336, 336],
-    "dinosiglip-vit-so-224px": [224, 224],
-    "dinosiglip-vit-so-384px": [384, 384],
-}
-VISION_BACKBONE_TO_TIMM_ID: Dict[str, List[str]] = {
-    "clip-vit-l": ["vit_large_patch14_clip_224.openai"],
-    "clip-vit-l-336px": ["vit_large_patch14_clip_336.openai"],
-
-    "dinov2-vit-l": ["vit_large_patch14_reg4_dinov2.lvd142m"],
-    "in1k-vit-l": ["vit_large_patch16_224.augreg_in21k_ft_in1k"],
-
-    "siglip-vit-so400m": ["vit_so400m_patch14_siglip_224"],
-    "siglip-vit-so400m-384px": ["vit_so400m_patch14_siglip_384"],
-
-    "dinoclip-vit-l-336px": ["vit_large_patch14_reg4_dinov2.lvd142m", "vit_large_patch14_clip_336.openai"],
-    "dinosiglip-vit-so-224px": ["vit_large_patch14_reg4_dinov2.lvd142m", "vit_so400m_patch14_siglip_224"],
-    "dinosiglip-vit-so-384px": ["vit_large_patch14_reg4_dinov2.lvd142m", "vit_so400m_patch14_siglip_384"],
-}
-TIMM_OVERRIDE_ACT_LAYER: Dict[str, List[Optional[str]]] = {
-    "clip-vit-l": ["quick_gelu"], "clip-vit-l-336px": ["quick_gelu"],
-    "dinov2-vit-l": [None], "in1k-vit-l": [None],
-    "siglip-vit-so400m": [None], "siglip-vit-so400m-384px": [None],
-    "dinoclip-vit-l-336px": [None, "quick_gelu"],
-    "dinosiglip-vit-so-224px": [None, None], "dinosiglip-vit-so-384px": [None, None]
-}
-
-LLM_BACKBONE_TO_HF_PATH = {
-    "llama2-7b-pure": "meta-llama/Llama-2-7b-hf", "llama2-13b-pure": "meta-llama/Llama-2-13b-hf",
-    "llama2-7b-chat": "meta-llama/Llama-2-7b-chat-hf", "llama2-13b-chat": "meta-llama/Llama-2-13b-chat-hf",
-    "llama3-1-8b-pure": "meta-llama/Meta-Llama-3.1-8B",
-
-    "vicuna-v15-7b": "lmsys/vicuna-7b-v1.5", "vicuna-v15-13b": "lmsys/vicuna-13b-v1.5",
-
-    "mistral-v0.1-7b-pure": "mistralai/Mistral-7B-v0.1",
-    "mistral-v0.1-7b-instruct": "mistralai/Mistral-7B-Instruct-v0.1",
-
-    "phi-2-3b": "microsoft/phi-2",
-}
-LLM_BACKBONE_TO_HF_METACLASS = {
-    "llama2-7b-pure": "llama", "llama2-13b-pure": "llama", "llama2-7b-chat": "llama", "llama2-13b-chat": "llama",
-    "vicuna-v15-7b": "llama", "vicuna-v15-13b": "llama", "llama3-1-8b-pure": "llama",
-
-    "mistral-v0.1-7b-pure": "mistral", "mistral-v0.1-7b-instruct": "mistral",
-
-    "phi-2-3b": "phi",
-}
-
-VALID_VISION_BACKBONES = set(VISION_BACKBONE_TO_RESOLUTION.keys())
-VALID_LLM_BACKBONES = set(LLM_BACKBONE_TO_HF_PATH)
-# fmt: on
-
-class PrismaticConfig(PretrainedConfig):
-    model_type: str = "prismatic"
-    is_composition: bool = False
-
-    def __init__(
-        self,
-        vision_backbone_id: str = "siglip-vit-so400m",
-        llm_backbone_id: str = "vicuna-v15-7b",
-        arch_specifier: str = "no-align+gelu-mlp",
-        use_fused_vision_backbone: Optional[bool] = None,
-        image_resize_strategy: str = "letterbox",
-        text_config: Optional[Dict[str, Any]] = None,
-        llm_max_length: int = 2048,
-        pad_token_id: int = 32000,
-        pad_to_multiple_of: int = 64,
-        output_projector_states: bool = False,
-        vocab_size: int = 32001,  # Ensure vocab_size is passed and set
-        **kwargs: str,
-    ) -> None:
-        if vision_backbone_id not in VALID_VISION_BACKBONES:
-            raise ValueError(f"Vision backbone `{vision_backbone_id}` not in {VALID_VISION_BACKBONES = }")
-
-        if llm_backbone_id not in VALID_LLM_BACKBONES:
-            raise ValueError(f"LLM backbone `{llm_backbone_id}` not in {VALID_LLM_BACKBONES = }")
-
-        # Set Prismatic Configuration Fields
-        self.vision_backbone_id = vision_backbone_id
-        self.llm_backbone_id = llm_backbone_id
-        self.arch_specifier = arch_specifier
-        self.output_projector_states = output_projector_states
-        self.vocab_size = vocab_size
-
-        # [Contract] All vision backbone parameters are lists =>> supports fused backbones with different preprocessing
-        self.use_fused_vision_backbone = (
-            use_fused_vision_backbone
-            if use_fused_vision_backbone is not None
-            else any(self.vision_backbone_id.startswith(v) for v in ["dinoclip", "dinosiglip"])
-        )
-
-        self.timm_model_ids = VISION_BACKBONE_TO_TIMM_ID[self.vision_backbone_id]
-        self.timm_override_act_layers = TIMM_OVERRIDE_ACT_LAYER[self.vision_backbone_id]
-        self.image_sizes = VISION_BACKBONE_TO_RESOLUTION[self.vision_backbone_id]
-        self.image_resize_strategy = image_resize_strategy
-
-        self.hf_llm_id = LLM_BACKBONE_TO_HF_PATH[self.llm_backbone_id]
-        self.llm_max_length = llm_max_length
-        self.pad_token_id, self.pad_to_multiple_of = pad_token_id, pad_to_multiple_of
-
-        # Set padding_idx if not already set
-        if not hasattr(self, 'padding_idx'):
-        #    self.padding_idx = pad_token_id
-             self.padding_idx = 0
-
-        # [IMPORTANT] HF Utilities actually look for a `text_config` field... we need to use that specific naming!
-        self.text_config = (
-            CONFIG_MAPPING[LLM_BACKBONE_TO_HF_METACLASS[self.llm_backbone_id]](**text_config)
-            if text_config is not None
-            else CONFIG_MAPPING[LLM_BACKBONE_TO_HF_METACLASS[self.llm_backbone_id]]()
-        )
-
-        # Dispatch **kwargs to super() =>> note that `pad_token_id` collides, so we pass it in here as well...
-        super().__init__(pad_token_id=pad_token_id, vocab_size=vocab_size, **kwargs)
-
-
-class OpenVLAConfig(PrismaticConfig):
-    model_type: str = "openvla"
-
-    def __init__(
-        self,
-        norm_stats: Optional[Dict[str, Dict[str, Dict[str, Dict[str, List[float]]]]]] = None,
-        n_action_bins: int = 256,
-        vocab_size: int = 32001,  # Default vocab size, adjust if necessary
-        **kwargs: str,
-    ) -> None:
-        self.norm_stats = norm_stats
-        self.n_action_bins = n_action_bins
-        self.vocab_size = vocab_size
-
-        super().__init__(**kwargs)
-
-        # Ensure padding_idx is within the valid range
-        if not hasattr(self, 'padding_idx') or self.padding_idx >= self.vocab_size:
-            print(f"Padding index {self.padding_idx} is out of range. Adjusting to {self.vocab_size - 1}.")
-            self.padding_idx = self.vocab_size - 1
-

generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 0,
-  "transformers_version": "4.43.3"
-}

model-00001-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3320560cf3d9df5fce1814090c8efa3b2f7dc871de4caed2801065eebc5776a4
-size 6925858176

model-00002-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:053801444d3f2a3d2b26272ac2a0ecdc852755b85183a8554fd3996b00670abb
-size 6971232040

model-00003-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e96176e2d79eb5fd2064dbf93b7a2af7ec086fbe58ba36bccfe34957c83c526d
-size 2758374672

model.safetensors.index.json

@@ -1,989 +0,0 @@
-{
-  "metadata": {
-    "total_size": 16655338368
-  },
-  "weight_map": {
-    "language_model.lm_head.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
-    "projector.fc1.bias": "model-00001-of-00003.safetensors",
-    "projector.fc1.weight": "model-00001-of-00003.safetensors",
-    "projector.fc2.bias": "model-00001-of-00003.safetensors",
-    "projector.fc2.weight": "model-00001-of-00003.safetensors",
-    "projector.fc3.bias": "model-00001-of-00003.safetensors",
-    "projector.fc3.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.ls1.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.ls2.scale_factor": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.cls_token": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.norm.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.norm.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.pos_embed": "model-00001-of-00003.safetensors",
-    "vision_backbone.featurizer.reg_token": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.kv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.kv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.latent": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.norm.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.norm.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.q.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.attn_pool.q.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.norm.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.norm.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
-    "vision_backbone.fused_featurizer.pos_embed": "model-00001-of-00003.safetensors"
-  }
-}

modeling_prismatic.py

@@ -1,570 +0,0 @@
-"""
-modeling_prismatic.py
-
-Core HuggingFace-style PrismaticPreTrainedModel and PrismaticForConditionalGeneration class definitions, inheriting
-from the default `transformers.PretrainedModel`. Meant to be standalone and self-contained, but exactly replicate the
-logic in `prismatic.models.vlms.prismatic.py`.
-
-Note =>> for the time being, not adding the custom HF "docstring" formatting.
-
-References [LLaVa, IDEFICS-2]:
-    => https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/modeling_llava.py
-    => https://github.com/huggingface/transformers/blob/main/src/transformers/models/idefics2/modeling_idefics2.py
-"""
-
-import logging
-from dataclasses import dataclass
-from functools import partial
-from typing import Any, Callable, ClassVar, Dict, List, Optional, Tuple, Union
-
-import numpy as np
-import timm
-import tokenizers
-import torch
-import torch.nn as nn
-import transformers
-from timm.models.vision_transformer import LayerScale
-from transformers import AutoModelForCausalLM, PretrainedConfig, PreTrainedModel
-from transformers.modeling_outputs import ModelOutput
-
-from .configuration_prismatic import OpenVLAConfig, PrismaticConfig
-
-# Get Logger
-logger = logging.getLogger(__name__)
-
-
-# === PyTorch/HuggingFace Default IGNORE_INDEX (for CrossEntropyLoss labels)
-IGNORE_INDEX = -100
-
-
-# === Utility Functions for Monkey-Patching ===
-def unpack_tuple(fn: Callable[[Any], Tuple[Any]]) -> Callable[[Any], Any]:
-    def wrapper(*args: Any, **kwargs: Any) -> Any:
-        result = fn(*args, **kwargs)
-        return result[0] if isinstance(result, tuple) else result
-
-    return wrapper
-
-
-# HF Transformers overwrites parameters with names containing `gamma`; we're going to patch VisionBackbone.LayerScale.
-#   =>> TIMM :: https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/vision_transformer.py#L109
-#   =>> Transformers :: https://github.com/huggingface/transformers/blob/main/src/transformers/modeling_utils.py#L3960
-def _ls_new_forward(self, x: torch.Tensor) -> torch.Tensor:
-    return x.mul_(self.scale_factor) if self.inplace else x * self.scale_factor
-
-
-def ls_apply_patch(ls_module: LayerScale):
-    ls_module.scale_factor = nn.Parameter(ls_module.gamma.clone())
-    ls_module.forward = _ls_new_forward.__get__(ls_module, LayerScale)
-    del ls_module.gamma
-
-
-# === Prismatic Vision Backbone (nn.Module) Definitions (w/ Fused Backbone Support) ===
-class PrismaticVisionBackbone(nn.Module):
-    def __init__(
-        self,
-        use_fused_vision_backbone: bool,
-        image_sizes: List[int],
-        timm_model_ids: List[str],
-        timm_override_act_layers: List[Optional[str]],
-    ) -> None:
-        super().__init__()
-        self.use_fused_vision_backbone = use_fused_vision_backbone
-
-        # [Contract] Validate number of (fused) vision backbones, create "alpha" featurizer and Instantiate
-        #   =>> Note :: Monkey-Patch the `forward()` function of the backbone to ensure FSDP-compatibility
-        #               Hardcodes `get_intermediate_layers` to return the **SECOND-TO-LAST** layer patches!
-        assert len(timm_model_ids) <= 2, "Prismatic models only support up to 2 (fused) vision backbones!"
-        self.featurizer = timm.create_model(
-            timm_model_ids[0],
-            pretrained=False,
-            num_classes=0,
-            img_size=image_sizes[0],
-            act_layer=timm_override_act_layers[0],
-        )
-        self.featurizer.forward = unpack_tuple(
-            partial(self.featurizer.get_intermediate_layers, n={len(self.featurizer.blocks) - 2})
-        )
-        self.embed_dim = self.featurizer.embed_dim
-
-        # If `use_fused_vision_backbone` =>> create "beta" featurizer
-        if self.use_fused_vision_backbone:
-            self.fused_featurizer = timm.create_model(
-                timm_model_ids[1],
-                pretrained=False,
-                num_classes=0,
-                img_size=image_sizes[1],
-                act_layer=timm_override_act_layers[1],
-            )
-            self.fused_featurizer.forward = unpack_tuple(
-                partial(self.fused_featurizer.get_intermediate_layers, n={len(self.fused_featurizer.blocks) - 2})
-            )
-            self.embed_dim += self.fused_featurizer.embed_dim
-
-        # Patch `vision_backbone.featurizer` and `vision_backbone.fused_featurizer` with HF-Compatible LayerScale
-        for module in self.featurizer.modules():
-            if isinstance(module, LayerScale):
-                ls_apply_patch(module)
-
-        if self.use_fused_vision_backbone:
-            for module in self.fused_featurizer.modules():
-                if isinstance(module, LayerScale):
-                    ls_apply_patch(module)
-
-    def forward(self, pixel_values: torch.Tensor) -> torch.Tensor:
-        """Run image (`pixel_values`) through featurizer; if channel-stacked, then dispatch and sequence stack."""
-        if not self.use_fused_vision_backbone:
-            return self.featurizer(pixel_values)
-
-        # Split `pixel_values :: [bsz, 2 * 3, resolution, resolution]` =>> featurize =>> channel stack
-        img, img_fused = torch.split(pixel_values, [3, 3], dim=1)
-        patches, patches_fused = self.featurizer(img), self.fused_featurizer(img_fused)
-
-        return torch.cat([patches, patches_fused], dim=2)
-
-
-# === Prismatic Projector (nn.Module) Definitions ===
-class PrismaticProjector(nn.Module):
-    def __init__(self, use_fused_vision_backbone: bool, vision_dim: int, llm_dim: int) -> None:
-        super().__init__()
-        self.use_fused_vision_backbone = use_fused_vision_backbone
-        self.vision_dim, self.llm_dim = vision_dim, llm_dim
-
-        # Switch on `use_fused_vision_backbone` =>> use slightly different MLPs and projection factors!
-        if not self.use_fused_vision_backbone:
-            self.fc1 = nn.Linear(self.vision_dim, self.llm_dim, bias=True)
-            self.fc2 = nn.Linear(self.llm_dim, self.llm_dim, bias=True)
-            self.act_fn1 = nn.GELU()
-        else:
-            initial_projection_dim = 4 * vision_dim
-            self.fc1 = nn.Linear(self.vision_dim, initial_projection_dim, bias=True)
-            self.fc2 = nn.Linear(initial_projection_dim, self.llm_dim, bias=True)
-            self.fc3 = nn.Linear(self.llm_dim, self.llm_dim, bias=True)
-            self.act_fn1 = nn.GELU()
-            self.act_fn2 = nn.GELU()
-
-    def forward(self, img_patches: torch.Tensor) -> torch.Tensor:
-        if not self.use_fused_vision_backbone:
-            projected_features = self.fc1(img_patches)
-            projected_features = self.act_fn1(projected_features)
-            projected_features = self.fc2(projected_features)
-        else:
-            projected_features = self.fc1(img_patches)
-            projected_features = self.act_fn1(projected_features)
-            projected_features = self.fc2(projected_features)
-            projected_features = self.act_fn2(projected_features)
-            projected_features = self.fc3(projected_features)
-
-        return projected_features
-
-
-# === Main HF Class Definitions ===
-@dataclass
-class PrismaticCausalLMOutputWithPast(ModelOutput):
-    """Base class for Prismatic casual (visually-conditioned) language model outputs; also exposes visual features."""
-
-    loss: Optional[torch.FloatTensor] = None
-    logits: torch.FloatTensor = None
-    past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None
-    hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
-    attentions: Optional[Tuple[torch.FloatTensor]] = None
-
-    # Additions for VLMs
-    projector_features: Optional[torch.FloatTensor] = None
-
-
-class PrismaticPreTrainedModel(PreTrainedModel):
-    config_class: PretrainedConfig = PrismaticConfig
-    base_model_prefix: str = "model"
-    supports_gradient_checkpointing: bool = True
-
-    _no_split_modules: ClassVar[List[str]] = ["PrismaticProjector"]
-    _skip_keys_device_placement: str = "past_key_values"
-    _supports_flash_attn_2: bool = True
-
-    def _init_weights(self, module: nn.Module) -> None:
-        # Important :: this HF ported version is *not* meant for training from scratch; only inference and fine-tuning!
-        #   => As such, this init_weights code is not correct; if training VLMs from scratch, use the main codebase at
-        #      https://github.com/TRI-ML/prismatic-vlms
-        std = (
-            self.config.initializer_range
-            if hasattr(self.config, "initializer_range")
-            else self.config.text_config.initializer_range
-        )
-
-        if hasattr(module, "class_embedding"):
-            module.class_embedding.data.normal_(mean=0.0, std=std)
-
-        if isinstance(module, (nn.Linear, nn.Conv2d)):
-            module.weight.data.normal_(mean=0.0, std=std)
-            if module.bias is not None:
-                module.bias.data.zero_()
-        elif isinstance(module, nn.Embedding):
-            module.weight.data.normal_(mean=0.0, std=std)
-            if module.padding_idx is not None:
-                module.weight.data[module.padding_idx].zero_()
-
-    @property
-    def _supports_sdpa(self) -> bool:
-        """Check LLM supports SDPA Attention"""
-        return self.language_model._supports_sdpa
-
-
-class PrismaticForConditionalGeneration(PrismaticPreTrainedModel):
-    def __init__(self, config: PrismaticConfig) -> None:
-        super().__init__(config)
-
-        # [Validation] Lightweight Validate on `config` Fields + Dependency Versions
-        if config.use_fused_vision_backbone is None:
-            raise ValueError("Missing config field `use_fused_vision_backbone`")
-
-        if timm.__version__ not in {"0.9.10", "0.9.11", "0.9.12", "0.9.16"}:
-            raise NotImplementedError(
-                "TIMM Version must be >= 0.9.10 and < 1.0.0 (breaking); please raise a GitHub Issue "
-                "if you urgently need support for latest TIMM versions."
-            )
-
-        if (transformers.__version__ != "4.40.1") or (tokenizers.__version__ != "0.19.1"):
-            logger.warning(
-                f"Expected `transformers==4.40.1` and `tokenizers==0.19.1` but got "
-                f"`transformers=={transformers.__version__}` and `tokenizers=={tokenizers.__version__}`; "
-                f"there might be inference-time regressions due to dependency changes. If in doubt, please"
-                f"use the above versions."
-            )
-
-        # Instantiate PrismaticVisionBackbone (w/ Potential Fused Backbone)
-        self.vision_backbone = PrismaticVisionBackbone(
-            config.use_fused_vision_backbone, config.image_sizes, config.timm_model_ids, config.timm_override_act_layers
-        )
-
-        # Create Multimodal Projector
-        self.projector = PrismaticProjector(
-            config.use_fused_vision_backbone,
-            vision_dim=self.vision_backbone.embed_dim,
-            llm_dim=config.text_config.hidden_size,
-        )
-
-        print("CONFIG: ", config)
-        print("CONFIG text: ", config.text_config)
-        print("CONFIG attn implementation: ", config._attn_implementation)
-        # Instantiate LLM Backbone
-        self.language_model = AutoModelForCausalLM.from_config(
-            config.text_config, attn_implementation=config._attn_implementation
-        )
-        print("loaded language model: ", self.language_model)
-        #self.language_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B")
-        self.vocab_size = config.text_config.vocab_size
-        self.pad_token_id = config.pad_token_id
-
-        # HF Boilerplate =>> initializes weights via `_init_weights()` and sets gradient checkpointing
-        self.post_init()
-
-    # === `PreTrainedModel` Boilerplate ===
-    def get_input_embeddings(self) -> nn.Module:
-        return self.language_model.get_input_embeddings()
-
-    def set_input_embeddings(self, value: nn.Module) -> None:
-        self.language_model.set_input_embeddings(value)
-
-    def get_output_embeddings(self) -> nn.Module:
-        return self.language_model.get_output_embeddings()
-
-    def set_output_embeddings(self, new_embeddings: nn.Module) -> None:
-        self.language_model.set_output_embeddings(new_embeddings)
-
-    def get_decoder(self) -> nn.Module:
-        return self.language_model.get_decoder()
-
-    def set_decoder(self, decoder: nn.Module) -> None:
-        self.language_model.set_decoder(decoder)
-
-    def tie_weights(self) -> None:
-        self.language_model.tie_weights()  # Note: `Llama-2` and `Mistral` don't tie weights (no-op)
-
-    def resize_token_embeddings(
-        self, new_num_tokens: Optional[int] = None, pad_to_multiple_of: Optional[int] = None
-    ) -> nn.Embedding:
-        updated_embeddings = self.language_model.resize_token_embeddings(new_num_tokens, pad_to_multiple_of)
-
-        # Update config/instance variables
-        self.config.text_config.vocab_size = updated_embeddings.num_embeddings
-        self.vocab_size = updated_embeddings.num_embeddings
-
-        return updated_embeddings
-
-    # === Core Prismatic VLM `forward()` Logic ===
-    def forward(
-        self,
-        input_ids: Optional[torch.LongTensor] = None,
-        attention_mask: Optional[torch.Tensor] = None,
-        pixel_values: Optional[torch.FloatTensor] = None,
-        labels: Optional[torch.LongTensor] = None,
-        inputs_embeds: Optional[torch.FloatTensor] = None,
-        past_key_values: Optional[List[torch.FloatTensor]] = None,
-        use_cache: Optional[bool] = None,
-        output_attentions: Optional[bool] = None,
-        output_hidden_states: Optional[bool] = None,
-        output_projector_features: Optional[bool] = None,
-        return_dict: Optional[bool] = None,
-    ) -> Union[Tuple, PrismaticCausalLMOutputWithPast]:
-        """Run a forward pass through the VLM, returning a PrismaticCausalLMOutputWithPast instance."""
-        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
-        output_hidden_states = (
-            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
-        )
-        output_projector_features = output_projector_features if output_projector_features is not None else False
-        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
-
-        # Respect `use_cache` only if not training (even if `gradient_checkpointing` is off)
-        use_cache = use_cache and not self.training
-
-        # Instantiate Placeholder for Projector Features
-        projected_patch_embeddings = None
-
-        # Note :: We only support forward passes with the following cases:
-        #   => Cached Generation :: (input_ids.shape[1] == 1) and (past_key_values is not None)
-        #   => Unimodal Forward :: (pixel_values is None)
-        #   => Multimodal Forward :: (pixel_values is not None) and (input_ids/embeds.shape[0] == pixel_values.shape[0])
-
-        # === Handle Generation with Cache (`input_ids.shape[1] == 1`) =>> requires `past_keys_values` ===
-        if input_ids.shape[1] == 1:
-            assert input_ids.shape[0] == 1, "Generation is only currently supported for batch size of 1!"
-            assert past_key_values is not None, "You must provide `past_key_values` during cached generation!"
-            assert labels is None, "Unexpected key `labels` provided during cached generation!"
-
-            language_model_output = self.language_model(
-                input_ids=input_ids,
-                attention_mask=None,
-                position_ids=None,
-                past_key_values=past_key_values,
-                inputs_embeds=None,
-                labels=None,
-                use_cache=use_cache,
-                output_attentions=output_attentions,
-                output_hidden_states=output_hidden_states,
-                return_dict=return_dict,
-            )
-
-        # === Handle Unimodal Forward ===
-        elif pixel_values is None:
-            assert (input_ids is not None) and (inputs_embeds is None), "Missing `input_ids` in language-only forward!"
-            assert past_key_values is None, "Unexpected key `past_key_values` provided during language-only forward!"
-
-            language_model_output = self.language_model(
-                input_ids=input_ids,
-                attention_mask=attention_mask,
-                position_ids=None,
-                past_key_values=None,
-                inputs_embeds=None,
-                labels=labels,
-                use_cache=use_cache,
-                output_attentions=output_attentions,
-                output_hidden_states=output_hidden_states,
-                return_dict=return_dict,
-            )
-
-        # === Handle Multimodal Forward ===
-        elif (input_ids.shape[0] == pixel_values.shape[0]) or (inputs_embeds.shape[0] == pixel_values.shape[0]):
-            assert past_key_values is None, "Unexpected key `past_key_values` provided during language-only forward!"
-
-            # Visual Feature Extraction
-            patch_features = self.vision_backbone(pixel_values)
-
-            # Projection Logic =>> Update Attention Mask
-            projected_patch_embeddings = self.projector(patch_features)
-            projected_patch_attention_mask = None
-            if attention_mask is not None:
-                projected_patch_attention_mask = torch.full(
-                    (projected_patch_embeddings.shape[0], projected_patch_embeddings.shape[1]),
-                    fill_value=True,
-                    dtype=attention_mask.dtype,
-                    device=attention_mask.device,
-                )
-
-            # Get Input Embeddings (from Language Model Embeddings)
-            input_embeddings = self.get_input_embeddings()(input_ids)
-
-            # Build Multimodal Embeddings & Attention Mask =>> Prismatic defaults to inserting after <BOS> token (1:)
-            multimodal_embeddings = torch.cat(
-                [input_embeddings[:, :1, :], projected_patch_embeddings, input_embeddings[:, 1:, :]], dim=1
-            )
-            multimodal_attention_mask = None
-            if attention_mask is not None:
-                multimodal_attention_mask = torch.cat(
-                    [attention_mask[:, :1], projected_patch_attention_mask, attention_mask[:, 1:]], dim=1
-                )
-
-            # Build Labels (if specified) =>> Ignore Labels for Patch Embeddings
-            multimodal_labels = None
-            if labels is not None:
-                projected_patch_labels = torch.full(
-                    (projected_patch_embeddings.shape[0], projected_patch_embeddings.shape[1]),
-                    fill_value=IGNORE_INDEX,
-                    dtype=labels.dtype,
-                    device=labels.device,
-                )
-                multimodal_labels = torch.cat([labels[:, :1], projected_patch_labels, labels[:, 1:]], dim=1)
-
-            # Dispatch to Language Model
-            language_model_output = self.language_model(
-                input_ids=None,
-                attention_mask=multimodal_attention_mask,
-                position_ids=None,
-                past_key_values=None,
-                inputs_embeds=multimodal_embeddings,
-                labels=multimodal_labels,
-                use_cache=use_cache,
-                output_attentions=output_attentions,
-                output_hidden_states=output_hidden_states,
-                return_dict=return_dict,
-            )
-
-        # === Otherwise =>> Assume Invalid! ===
-        elif (input_ids.shape[0] != pixel_values.shape[0]) or (inputs_embeds.shape[0] != pixel_values.shape[0]):
-            raise ValueError("Non-homogenous batch of (text, image) input -- forward() does not support mixed batches!")
-
-        else:
-            raise ValueError(
-                "Invalid PrismaticForConditionalGeneration `forward()` call with provided arguments:\n"
-                f"=> `input_ids` = {input_ids is not None}\n"
-                f"=> `attention_mask` = {attention_mask is not None}\n"
-                f"=> `pixel_values` = {pixel_values is not None}\n"
-                f"=> `labels` = {labels is not None}\n"
-                f"=> `input_embeds` = {inputs_embeds is not None}\n"
-                f"=> `past_key_values` = {past_key_values is not None}\n"
-                f"=> `use_cache` = {use_cache}"
-            )
-
-        # Unpack `language_model_output` and return PrismaticCausalLMOutputWithPast (or tuple if not `return_dict`)
-        if not return_dict:
-            if output_projector_features and (projected_patch_embeddings is not None):
-                return *language_model_output, projected_patch_embeddings
-
-            return language_model_output
-
-        return PrismaticCausalLMOutputWithPast(
-            loss=language_model_output.loss,
-            logits=language_model_output.logits,
-            past_key_values=language_model_output.past_key_values,
-            hidden_states=language_model_output.hidden_states,
-            attentions=language_model_output.attentions,
-            projector_features=projected_patch_embeddings,
-        )
-
-    # === GenerationMixin Methods ===
-    def prepare_inputs_for_generation(
-        self,
-        input_ids: Optional[torch.Tensor] = None,
-        past_key_values: Optional[List[torch.FloatTensor]] = None,
-        inputs_embeds: Optional[torch.FloatTensor] = None,
-        pixel_values: Optional[torch.FloatTensor] = None,
-        attention_mask: Optional[torch.Tensor] = None,
-        **kwargs: str,
-    ) -> Dict[str, torch.Tensor]:
-        """Borrowed from `LlamaForCausalLM` and simplified for batch size = 1; mirrors original PrismaticVLM logic."""
-        if ((input_ids is not None) and (input_ids.shape[0] > 1)) or (
-            (inputs_embeds is not None) and (inputs_embeds.shape[0] > 1)
-        ):
-            raise ValueError("Generation with batch size > 1 is not currently supported!")
-
-        # Handle `past_key_values` (cache) =>> assume `input_ids` just has unprocessed tokens
-        if past_key_values is not None:
-            input_ids = input_ids[:, -1:]
-
-        # If `input_embeds` are passed, we only want to use them in the 1st generation step
-        if inputs_embeds is not None and past_key_values is None:
-            model_inputs = {"input_embeds": inputs_embeds}
-        else:
-            model_inputs = {"input_ids": input_ids}
-
-        # Make sure `pixel_values` are preserved in `model_inputs`
-        model_inputs.update(
-            {
-                "attention_mask": attention_mask,
-                "pixel_values": pixel_values,
-                "past_key_values": past_key_values,
-                "use_cache": kwargs.get("use_cache"),
-            }
-        )
-
-        return model_inputs
-
-    # Defer to Language Model (all handle this differently, with different return types)
-    def _reorder_cache(self, *args, **kwargs) -> Any:
-        return self.language_model._reorder_cache(*args, **kwargs)
-
-
-class OpenVLAForActionPrediction(PrismaticForConditionalGeneration):
-    config_class: PretrainedConfig = OpenVLAConfig
-
-    def __init__(self, config: OpenVLAConfig) -> None:
-        super().__init__(config)
-        self.norm_stats = config.norm_stats
-
-        # Compute action bins
-        self.bins = np.linspace(-1, 1, config.n_action_bins)
-        self.bin_centers = (self.bins[:-1] + self.bins[1:]) / 2.0
-
-        # Compute vocab size for de-tokenization -- revert added "multiple of"
-        self.vocab_size = self.config.text_config.vocab_size - self.config.pad_to_multiple_of
-
-    def predict_action(
-        self, input_ids: Optional[torch.LongTensor] = None, unnorm_key: Optional[str] = None, **kwargs: str
-    ) -> np.ndarray:
-        """Thin wrapper around super().generate() that decodes predicted actions and de-normalizes them."""
-
-        # We need to add this special empty token ('') after the colon (':') token in "ASSISTANT:"
-        # in order for the predictions to match the training configuration and be accurate.
-        input_ids = torch.cat(
-            (input_ids, torch.unsqueeze(torch.Tensor([29871]).long(), dim=0).to(input_ids.device)), dim=1
-        )
-
-        # Run VLA inference
-        generated_ids = self.generate(input_ids, max_new_tokens=self.get_action_dim(unnorm_key), **kwargs)
-
-        # Extract predicted action tokens and translate into (normalized) continuous actions
-        predicted_action_token_ids = generated_ids[0, -self.get_action_dim(unnorm_key) :].cpu().numpy()
-        discretized_actions = self.vocab_size - predicted_action_token_ids
-        discretized_actions = np.clip(discretized_actions - 1, a_min=0, a_max=self.bin_centers.shape[0] - 1)
-        normalized_actions = self.bin_centers[discretized_actions]
-
-        # Unnormalize actions
-        action_norm_stats = self.get_action_stats(unnorm_key)
-        mask = action_norm_stats.get("mask", np.ones_like(action_norm_stats["q01"], dtype=bool))
-        action_high, action_low = np.array(action_norm_stats["q99"]), np.array(action_norm_stats["q01"])
-        actions = np.where(
-            mask,
-            0.5 * (normalized_actions + 1) * (action_high - action_low) + action_low,
-            normalized_actions,
-        )
-
-        return actions
-
-    @staticmethod
-    def _check_unnorm_key(norm_stats: Dict[str, Dict[str, Any]], unnorm_key: Optional[str]) -> str:
-        if unnorm_key is None and len(norm_stats) != 1:
-            raise ValueError(
-                f"Your model was trained on more than one dataset. "
-                f"Please pass a `unnorm_key` from the following options to choose the statistics used for "
-                f"de-normalizing actions: {norm_stats.keys()}"
-            )
-
-        # If None, grab the (singular) dataset in `norm_stats` to use as `unnorm_key`
-        unnorm_key = unnorm_key if unnorm_key is not None else next(iter(norm_stats.keys()))
-        if unnorm_key not in norm_stats:
-            raise ValueError(
-                f"The `unnorm_key` you chose ({unnorm_key = }) is not in the available statistics. "
-                f"Please choose from: {norm_stats.keys()}"
-            )
-
-        return unnorm_key
-
-    def get_action_dim(self, unnorm_key: Optional[str] = None) -> int:
-        """Get the dimensionality of the policy's action space."""
-        unnorm_key = self._check_unnorm_key(self.norm_stats, unnorm_key)
-        return len(self.norm_stats[unnorm_key]["action"]["q01"])
-
-    def get_action_stats(self, unnorm_key: Optional[str] = None) -> Dict[str, Any]:
-        """Get all the logged statistics for the given dataset."""
-        unnorm_key = self._check_unnorm_key(self.norm_stats, unnorm_key)
-        return self.norm_stats[unnorm_key]["action"]

preprocessor_config.json

@@ -1,112 +0,0 @@
-{
-  "auto_map": {
-    "AutoImageProcessor": "processing_prismatic.PrismaticImageProcessor",
-    "AutoProcessor": "processing_prismatic.PrismaticProcessor"
-  },
-  "image_processor_type": "PrismaticImageProcessor",
-  "image_resize_strategy": "letterbox",
-  "input_sizes": [
-    [
-      3,
-      224,
-      224
-    ],
-    [
-      3,
-      224,
-      224
-    ]
-  ],
-  "interpolations": [
-    "bicubic",
-    "bicubic"
-  ],
-  "means": [
-    [
-      0.485,
-      0.456,
-      0.406
-    ],
-    [
-      0.5,
-      0.5,
-      0.5
-    ]
-  ],
-  "processor_class": "PrismaticProcessor",
-  "stds": [
-    [
-      0.229,
-      0.224,
-      0.225
-    ],
-    [
-      0.5,
-      0.5,
-      0.5
-    ]
-  ],
-  "tvf_crop_params": [
-    {
-      "output_size": [
-        224,
-        224
-      ]
-    },
-    {
-      "output_size": [
-        224,
-        224
-      ]
-    }
-  ],
-  "tvf_do_letterbox": true,
-  "tvf_letterbox_fill": [
-    127,
-    127,
-    127
-  ],
-  "tvf_normalize_params": [
-    {
-      "inplace": false,
-      "mean": [
-        0.484375,
-        0.455078125,
-        0.40625
-      ],
-      "std": [
-        0.228515625,
-        0.2236328125,
-        0.224609375
-      ]
-    },
-    {
-      "inplace": false,
-      "mean": [
-        0.5,
-        0.5,
-        0.5
-      ],
-      "std": [
-        0.5,
-        0.5,
-        0.5
-      ]
-    }
-  ],
-  "tvf_resize_params": [
-    {
-      "antialias": true,
-      "interpolation": 3,
-      "max_size": null,
-      "size": 224
-    },
-    {
-      "antialias": true,
-      "interpolation": 3,
-      "max_size": null,
-      "size": 224
-    }
-  ],
-  "use_fused_vision_backbone": true
-}

processing_prismatic.py

@@ -1,252 +0,0 @@
-"""
-processing_prismatic.py
-
-HuggingFace-style preprocessor definitions for Prismatic VLMs, inheriting from `ProcessorMixin`. Default configuration
-specifies `siglip-224px+7b`.
-"""
-
-from typing import Any, ClassVar, List, Optional, Tuple, Union
-
-import timm.data
-import torch
-import torchvision.transforms.functional as TVF
-from PIL import Image
-from torchvision.transforms import CenterCrop, Compose, Normalize, Resize, ToTensor
-from transformers import PreTrainedTokenizerBase
-from transformers.image_processing_utils import BatchFeature, ImageProcessingMixin
-from transformers.processing_utils import ProcessorMixin
-from transformers.tokenization_utils import PaddingStrategy, PreTokenizedInput, TextInput, TruncationStrategy
-from transformers.utils import TensorType
-
-
-# === Image Processing ===
-def letterbox_pad_transform(image: Image.Image, padding_fill_value: Tuple[int, int, int]) -> Image.Image:
-    """Given a PIL.Image, pad to square by adding a symmetric border around the height/width."""
-    (w, h), max_wh = image.size, max(image.size)
-    horizontal_pad, vertical_pad = int((max_wh - w) / 2), int((max_wh - h) / 2)
-    padding = (horizontal_pad, vertical_pad, horizontal_pad, vertical_pad)
-
-    return TVF.pad(image, padding, fill=padding_fill_value, padding_mode="constant")
-
-
-class PrismaticImageProcessor(ImageProcessingMixin):
-    model_input_names: ClassVar[List[str]] = ["pixel_values"]
-
-    def __init__(
-        self,
-        use_fused_vision_backbone: bool = False,
-        image_resize_strategy: str = "letterbox",
-        input_sizes: Optional[List[Tuple[int, int, int]]] = None,
-        interpolations: Optional[List[str]] = None,
-        means: Optional[List[Tuple[float, float, float]]] = None,
-        stds: Optional[List[Tuple[float, float, float]]] = None,
-        **kwargs: str,
-    ) -> None:
-        """
-        Initialize a PrismaticImageProcessor as a wrapper around a torchvision transform; this transform will be
-        created by TIMM, and edited to follow our custom `image_resize_strategy` logic.
-        @param use_fused_vision_backbone: Boolean indicating single or fused (dual) vision backbone
-        @param image_resize_strategy: Prismatic image resize strategy in < resize-naive | resize-crop | letterbox >
-        @param input_size: [TIMM :: `data_cfg`] Input image size as tuple (channels, width, height)
-        @param interpolation: [TIMM :: `data_cfg`] Interpolation as string (default: "bicubic")
-        @param mean: [TIMM :: `data_cfg`] Normalization mean as float tuple (or two-tuple if `fused_backbone`)
-        @param std: [TIMM :: `data_cfg`] Normalization std as float tuple (or two-tuple if `fused_backbone`)
-        """
-        self.use_fused_vision_backbone = use_fused_vision_backbone
-        self.image_resize_strategy = image_resize_strategy
-
-        # Handle `None` default values
-        input_sizes = [(3, 224, 224)] if input_sizes is None else input_sizes
-        means = [(0.5, 0.5, 0.5)] if means is None else means
-        stds = [(0.5, 0.5, 0.5)] if stds is None else stds
-
-        # TIMM `data_cfg` Parameters
-        self.input_sizes, self.interpolations, self.means, self.stds = input_sizes, interpolations, means, stds
-
-        # Grab torchvision transforms via TIMM =>> need to parse for specific "functional" transform values!
-        self.tvf_resize_params, self.tvf_crop_params, self.tvf_normalize_params = [], [], []
-        self.tvf_do_letterbox, self.tvf_letterbox_fill = False, None
-
-        for idx in range(len(input_sizes)):
-            transform = timm.data.create_transform(
-                input_size=self.input_sizes[idx],
-                interpolation=self.interpolations[idx],
-                mean=self.means[idx],
-                std=self.stds[idx],
-                crop_pct=1.0,  # Set to 1.0 to ignore cropping (initial Resize sets `input_size`)
-                crop_mode="center",  # Default crop mode -- no-op when `crop_pct == 1.0`
-                is_training=False,  # No image augmentations when loading the transform!
-            )
-
-            # [Validation] Ensure appropriate transform structure, expected sizes
-            if not (
-                isinstance(transform, Compose)
-                and (len(transform.transforms) == 4)
-                and isinstance(transform.transforms[0], Resize)
-                and isinstance(transform.transforms[1], CenterCrop)
-                and isinstance(transform.transforms[2], ToTensor)
-                and isinstance(transform.transforms[3], Normalize)
-                and (transform.transforms[0].size == self.input_sizes[idx][-1])
-                and (transform.transforms[1].size == self.input_sizes[idx][-2:])
-            ):
-                raise ValueError(f"Unexpected TIMM image transformation structure/sizes: `{transform}`")
-
-            # HF Image Processors *must* be JSON-serializable; as such, cannot have torchvision. as an attribute.
-            #   => Instead, we're going to parse the transform and call "torchvision.transforms.functional" (`tvf`)
-            resize_t, crop_t, norm_t = transform.transforms[0], transform.transforms[1], transform.transforms[3]
-            self.tvf_resize_params.append(
-                {
-                    "size": resize_t.size,
-                    "interpolation": TVF.pil_modes_mapping[resize_t.interpolation],
-                    "max_size": None,
-                    "antialias": True,
-                }
-            )
-            self.tvf_crop_params.append({"output_size": crop_t.size})
-            self.tvf_normalize_params.append(
-                {
-                    "mean": norm_t.mean.float().numpy().tolist(),
-                    "std": norm_t.std.float().numpy().tolist(),
-                    "inplace": False,
-                }
-            )
-            self.tvf_do_letterbox, self.tvf_letterbox_fill = False, None
-
-            # Handle Prismatic `image_resize_strategy`
-            if self.image_resize_strategy == "resize-naive":
-                self.tvf_resize_params[idx]["size"] = (resize_t.size, resize_t.size)
-            elif self.image_resize_strategy == "letterbox":
-                self.tvf_do_letterbox, self.tvf_letterbox_fill = True, tuple([int(x * 255) for x in self.means[idx]])
-            elif self.image_resize_strategy == "resize-crop":
-                pass
-            else:
-                raise ValueError(f"Image resize strategy `{self.image_resize_strategy}` is not supported!")
-
-        # Dispatch **kwargs to super()
-        super().__init__(**kwargs)
-
-    def apply_transform(self, img: Image.Image) -> torch.Tensor:
-        """Apply `functional` variant of TIMM's Transform = Compose([Resize -> CenterCrop -> ToTensor -> Normalize])"""
-        if self.tvf_do_letterbox:
-            img = letterbox_pad_transform(img, self.tvf_letterbox_fill)
-
-        # [Contract] Fused Backbones expect "channel-stacked" inputs; we'll unpack on the model side!
-        imgs_t = []
-        for idx in range(len(self.input_sizes)):
-            img_idx = TVF.resize(img, **self.tvf_resize_params[idx])
-            img_idx = TVF.center_crop(img_idx, **self.tvf_crop_params[idx])
-            img_idx_t = TVF.to_tensor(img_idx)
-            img_idx_t = TVF.normalize(img_idx_t, **self.tvf_normalize_params[idx])
-            imgs_t.append(img_idx_t)
-
-        # [Contract] `imgs_t` is a list of Tensors of shape [3, input_size, input_size]; stack along dim = 0
-        img_t = torch.vstack(imgs_t)
-
-        return img_t
-
-    def preprocess(
-        self,
-        images: Union[Image.Image, List[Image.Image]],
-        return_tensors: Optional[Union[str, TensorType]] = None,
-        **_: str,
-    ) -> BatchFeature:
-        """
-        Preprocess an image (or batch of images); note that unlike the `transformers :: BaseImageProcessor` we
-        explicitly only handle PIL.Image.Image instances for simplicity.
-        @param images: A (batch of) PIL.Image.Image instance(s) to preprocess.
-        @param return_tensors: BatchFeature default Tensor format (e.g., "pt" for torch); if None, returns np.ndarray
-        @return: Instance of `transformers :: BatchFeature` with a single key "pixel_values"
-        """
-        if not isinstance(images, list):
-            images = [images]
-
-        # Apply `self.img_transform` to each image (will return list of torch.Tensors); stack into "batched" Tensor
-        pixel_values = torch.stack([self.apply_transform(img.convert("RGB")) for img in images])
-
-        # Return BatchFeature =>> note that for compatibility, constructor expects Dict[str, np.ndarray], so we convert
-        return BatchFeature(data={"pixel_values": pixel_values.float().numpy()}, tensor_type=return_tensors)
-
-    def __call__(self, images: Union[Image.Image, List[Image.Image]], **kwargs) -> BatchFeature:
-        return self.preprocess(images, **kwargs)
-
-
-# === PrismaticProcessor =>> Wraps both ImageProcessor and Tokenizer ===
-#   =>> https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/processing_llava.py
-class PrismaticProcessor(ProcessorMixin):
-    attributes: ClassVar[List[str]] = ["image_processor", "tokenizer"]
-    image_processor_class: str = "AutoImageProcessor"
-    tokenizer_class: str = "AutoTokenizer"
-
-    def __init__(
-        self,
-        image_processor: Optional[ImageProcessingMixin] = None,
-        tokenizer: Optional[PreTrainedTokenizerBase] = None,
-    ) -> None:
-        super().__init__(image_processor, tokenizer)
-
-    def __call__(
-        self,
-        text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]],
-        images: Union[Image.Image, List[Image.Image]],
-        padding: Union[bool, str, PaddingStrategy] = False,
-        truncation: Optional[Union[bool, str, TruncationStrategy]] = None,
-        max_length: Optional[int] = None,
-        return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
-    ) -> BatchFeature:
-        """
-        Preprocess a given (batch) of text/images for a Prismatic VLM; forwards text to the underlying LLM's tokenizer,
-        forwards images to PrismaticImageProcessor.
-        @param text: The (batch) of text to encode; must be a string or list of strings.
-        @param images: A (batch of) PIL.Image.Image instance(s) to preprocess.
-        @param padding: Sequence padding strategy (if multiple specified) in < True = "longest" | "max_length" | False >
-        @param truncation: Truncation strategy for the output sequences; requires `max_length` to be specified
-        @param max_length: Maximum length (in tokens) to truncate
-        @param return_tensors: Type of return tensors (usually "pt" or TensorType.PYTORCH)
-        @return: BatchFeature with keys for `input_ids`, `attention_mask` and `pixel_values`.
-        """
-        pixel_values = self.image_processor(images, return_tensors=return_tensors)["pixel_values"]
-        text_inputs = self.tokenizer(
-            text, return_tensors=return_tensors, padding=padding, truncation=truncation, max_length=max_length
-        )
-
-        # [Validate] Need same number of images and text inputs!
-        if pixel_values.shape[0] != text_inputs.input_ids.shape[0]:
-            raise ValueError("Batch is malformed; expected same number of images and text inputs!")
-
-        return BatchFeature(data={**text_inputs, "pixel_values": pixel_values})
-
-    # === Tokenizer Dispatch Utilities =>> check `PreTrainedTokenizerBase` for documentation ===
-    def batch_decode(
-        self,
-        sequences: Union[List[int], List[List[int]], torch.Tensor, Any],  # `Any` = np.ndarray | tf.Tensor
-        skip_special_tokens: bool = False,
-        clean_up_tokenization_spaces: Optional[bool] = None,
-        **kwargs: str,
-    ) -> List[str]:
-        return self.tokenizer.batch_decode(
-            sequences=sequences,
-            skip_special_tokens=skip_special_tokens,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs,
-        )
-
-    def decode(
-        self,
-        token_ids: Union[int, List[int], torch.Tensor, Any],  # `Any` = np.ndarray | tf.Tensor
-        skip_special_tokens: bool = False,
-        clean_up_tokenization_spaces: Optional[bool] = None,
-        **kwargs: str,
-    ) -> str:
-        return self.tokenizer.decode(
-            token_ids=token_ids,
-            skip_special_tokens=skip_special_tokens,
-            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
-            **kwargs,
-        )
-
-    @property
-    def model_input_names(self) -> List[str]:
-        tokenizer_input_names = self.tokenizer.model_input_names
-        image_processor_input_names = self.image_processor.model_input_names
-
-        return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))

processor_config.json

@@ -1,6 +0,0 @@
-{
-  "auto_map": {
-    "AutoProcessor": "processing_prismatic.PrismaticProcessor"
-  },
-  "processor_class": "PrismaticProcessor"
-}

special_tokens_map.json

@@ -1,23 +0,0 @@
-{
-  "bos_token": {
-    "content": "<|begin_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|end_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<PAD>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer_config.json

@@ -1,2074 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "128000": {
-      "content": "<|begin_of_text|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128001": {
-      "content": "<|end_of_text|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128002": {
-      "content": "<|reserved_special_token_0|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128003": {
-      "content": "<|reserved_special_token_1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128004": {
-      "content": "<|finetune_right_pad_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128005": {
-      "content": "<|reserved_special_token_2|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128006": {
-      "content": "<|start_header_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128007": {
-      "content": "<|end_header_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128008": {
-      "content": "<|eom_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128009": {
-      "content": "<|eot_id|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128010": {
-      "content": "<|python_tag|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128011": {
-      "content": "<|reserved_special_token_3|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128012": {
-      "content": "<|reserved_special_token_4|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128013": {
-      "content": "<|reserved_special_token_5|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128014": {
-      "content": "<|reserved_special_token_6|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128015": {
-      "content": "<|reserved_special_token_7|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128016": {
-      "content": "<|reserved_special_token_8|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128017": {
-      "content": "<|reserved_special_token_9|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128018": {
-      "content": "<|reserved_special_token_10|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128019": {
-      "content": "<|reserved_special_token_11|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128020": {
-      "content": "<|reserved_special_token_12|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128021": {
-      "content": "<|reserved_special_token_13|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128022": {
-      "content": "<|reserved_special_token_14|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128023": {
-      "content": "<|reserved_special_token_15|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128024": {
-      "content": "<|reserved_special_token_16|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128025": {
-      "content": "<|reserved_special_token_17|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128026": {
-      "content": "<|reserved_special_token_18|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128027": {
-      "content": "<|reserved_special_token_19|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128028": {
-      "content": "<|reserved_special_token_20|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128029": {
-      "content": "<|reserved_special_token_21|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128030": {
-      "content": "<|reserved_special_token_22|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128031": {
-      "content": "<|reserved_special_token_23|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128032": {
-      "content": "<|reserved_special_token_24|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128033": {
-      "content": "<|reserved_special_token_25|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128034": {
-      "content": "<|reserved_special_token_26|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128035": {
-      "content": "<|reserved_special_token_27|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128036": {
-      "content": "<|reserved_special_token_28|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128037": {
-      "content": "<|reserved_special_token_29|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128038": {
-      "content": "<|reserved_special_token_30|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128039": {
-      "content": "<|reserved_special_token_31|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128040": {
-      "content": "<|reserved_special_token_32|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128041": {
-      "content": "<|reserved_special_token_33|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128042": {
-      "content": "<|reserved_special_token_34|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128043": {
-      "content": "<|reserved_special_token_35|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128044": {
-      "content": "<|reserved_special_token_36|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128045": {
-      "content": "<|reserved_special_token_37|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128046": {
-      "content": "<|reserved_special_token_38|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128047": {
-      "content": "<|reserved_special_token_39|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128048": {
-      "content": "<|reserved_special_token_40|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128049": {
-      "content": "<|reserved_special_token_41|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128050": {
-      "content": "<|reserved_special_token_42|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128051": {
-      "content": "<|reserved_special_token_43|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128052": {
-      "content": "<|reserved_special_token_44|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128053": {
-      "content": "<|reserved_special_token_45|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128054": {
-      "content": "<|reserved_special_token_46|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128055": {
-      "content": "<|reserved_special_token_47|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128056": {
-      "content": "<|reserved_special_token_48|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128057": {
-      "content": "<|reserved_special_token_49|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128058": {
-      "content": "<|reserved_special_token_50|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128059": {
-      "content": "<|reserved_special_token_51|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128060": {
-      "content": "<|reserved_special_token_52|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128061": {
-      "content": "<|reserved_special_token_53|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128062": {
-      "content": "<|reserved_special_token_54|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128063": {
-      "content": "<|reserved_special_token_55|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128064": {
-      "content": "<|reserved_special_token_56|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128065": {
-      "content": "<|reserved_special_token_57|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128066": {
-      "content": "<|reserved_special_token_58|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128067": {
-      "content": "<|reserved_special_token_59|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128068": {
-      "content": "<|reserved_special_token_60|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128069": {
-      "content": "<|reserved_special_token_61|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128070": {
-      "content": "<|reserved_special_token_62|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128071": {
-      "content": "<|reserved_special_token_63|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128072": {
-      "content": "<|reserved_special_token_64|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128073": {
-      "content": "<|reserved_special_token_65|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128074": {
-      "content": "<|reserved_special_token_66|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128075": {
-      "content": "<|reserved_special_token_67|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128076": {
-      "content": "<|reserved_special_token_68|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128077": {
-      "content": "<|reserved_special_token_69|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128078": {
-      "content": "<|reserved_special_token_70|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128079": {
-      "content": "<|reserved_special_token_71|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128080": {
-      "content": "<|reserved_special_token_72|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128081": {
-      "content": "<|reserved_special_token_73|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128082": {
-      "content": "<|reserved_special_token_74|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128083": {
-      "content": "<|reserved_special_token_75|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128084": {
-      "content": "<|reserved_special_token_76|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128085": {
-      "content": "<|reserved_special_token_77|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128086": {
-      "content": "<|reserved_special_token_78|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128087": {
-      "content": "<|reserved_special_token_79|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128088": {
-      "content": "<|reserved_special_token_80|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128089": {
-      "content": "<|reserved_special_token_81|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128090": {
-      "content": "<|reserved_special_token_82|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128091": {
-      "content": "<|reserved_special_token_83|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128092": {
-      "content": "<|reserved_special_token_84|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128093": {
-      "content": "<|reserved_special_token_85|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128094": {
-      "content": "<|reserved_special_token_86|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128095": {
-      "content": "<|reserved_special_token_87|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128096": {
-      "content": "<|reserved_special_token_88|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128097": {
-      "content": "<|reserved_special_token_89|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128098": {
-      "content": "<|reserved_special_token_90|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128099": {
-      "content": "<|reserved_special_token_91|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128100": {
-      "content": "<|reserved_special_token_92|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128101": {
-      "content": "<|reserved_special_token_93|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128102": {
-      "content": "<|reserved_special_token_94|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128103": {
-      "content": "<|reserved_special_token_95|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128104": {
-      "content": "<|reserved_special_token_96|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128105": {
-      "content": "<|reserved_special_token_97|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128106": {
-      "content": "<|reserved_special_token_98|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128107": {
-      "content": "<|reserved_special_token_99|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128108": {
-      "content": "<|reserved_special_token_100|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128109": {
-      "content": "<|reserved_special_token_101|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128110": {
-      "content": "<|reserved_special_token_102|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128111": {
-      "content": "<|reserved_special_token_103|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128112": {
-      "content": "<|reserved_special_token_104|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128113": {
-      "content": "<|reserved_special_token_105|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128114": {
-      "content": "<|reserved_special_token_106|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128115": {
-      "content": "<|reserved_special_token_107|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128116": {
-      "content": "<|reserved_special_token_108|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128117": {
-      "content": "<|reserved_special_token_109|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128118": {
-      "content": "<|reserved_special_token_110|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128119": {
-      "content": "<|reserved_special_token_111|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128120": {
-      "content": "<|reserved_special_token_112|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128121": {
-      "content": "<|reserved_special_token_113|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128122": {
-      "content": "<|reserved_special_token_114|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128123": {
-      "content": "<|reserved_special_token_115|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128124": {
-      "content": "<|reserved_special_token_116|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128125": {
-      "content": "<|reserved_special_token_117|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128126": {
-      "content": "<|reserved_special_token_118|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128127": {
-      "content": "<|reserved_special_token_119|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128128": {
-      "content": "<|reserved_special_token_120|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128129": {
-      "content": "<|reserved_special_token_121|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128130": {
-      "content": "<|reserved_special_token_122|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128131": {
-      "content": "<|reserved_special_token_123|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128132": {
-      "content": "<|reserved_special_token_124|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128133": {
-      "content": "<|reserved_special_token_125|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128134": {
-      "content": "<|reserved_special_token_126|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128135": {
-      "content": "<|reserved_special_token_127|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128136": {
-      "content": "<|reserved_special_token_128|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128137": {
-      "content": "<|reserved_special_token_129|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128138": {
-      "content": "<|reserved_special_token_130|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128139": {
-      "content": "<|reserved_special_token_131|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128140": {
-      "content": "<|reserved_special_token_132|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128141": {
-      "content": "<|reserved_special_token_133|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128142": {
-      "content": "<|reserved_special_token_134|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128143": {
-      "content": "<|reserved_special_token_135|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128144": {
-      "content": "<|reserved_special_token_136|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128145": {
-      "content": "<|reserved_special_token_137|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128146": {
-      "content": "<|reserved_special_token_138|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128147": {
-      "content": "<|reserved_special_token_139|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128148": {
-      "content": "<|reserved_special_token_140|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128149": {
-      "content": "<|reserved_special_token_141|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128150": {
-      "content": "<|reserved_special_token_142|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128151": {
-      "content": "<|reserved_special_token_143|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128152": {
-      "content": "<|reserved_special_token_144|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128153": {
-      "content": "<|reserved_special_token_145|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128154": {
-      "content": "<|reserved_special_token_146|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128155": {
-      "content": "<|reserved_special_token_147|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128156": {
-      "content": "<|reserved_special_token_148|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128157": {
-      "content": "<|reserved_special_token_149|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128158": {
-      "content": "<|reserved_special_token_150|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128159": {
-      "content": "<|reserved_special_token_151|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128160": {
-      "content": "<|reserved_special_token_152|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128161": {
-      "content": "<|reserved_special_token_153|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128162": {
-      "content": "<|reserved_special_token_154|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128163": {
-      "content": "<|reserved_special_token_155|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128164": {
-      "content": "<|reserved_special_token_156|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128165": {
-      "content": "<|reserved_special_token_157|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128166": {
-      "content": "<|reserved_special_token_158|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128167": {
-      "content": "<|reserved_special_token_159|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128168": {
-      "content": "<|reserved_special_token_160|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128169": {
-      "content": "<|reserved_special_token_161|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128170": {
-      "content": "<|reserved_special_token_162|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128171": {
-      "content": "<|reserved_special_token_163|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128172": {
-      "content": "<|reserved_special_token_164|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128173": {
-      "content": "<|reserved_special_token_165|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128174": {
-      "content": "<|reserved_special_token_166|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128175": {
-      "content": "<|reserved_special_token_167|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128176": {
-      "content": "<|reserved_special_token_168|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128177": {
-      "content": "<|reserved_special_token_169|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128178": {
-      "content": "<|reserved_special_token_170|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128179": {
-      "content": "<|reserved_special_token_171|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128180": {
-      "content": "<|reserved_special_token_172|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128181": {
-      "content": "<|reserved_special_token_173|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128182": {
-      "content": "<|reserved_special_token_174|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128183": {
-      "content": "<|reserved_special_token_175|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128184": {
-      "content": "<|reserved_special_token_176|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128185": {
-      "content": "<|reserved_special_token_177|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128186": {
-      "content": "<|reserved_special_token_178|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128187": {
-      "content": "<|reserved_special_token_179|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128188": {
-      "content": "<|reserved_special_token_180|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128189": {
-      "content": "<|reserved_special_token_181|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128190": {
-      "content": "<|reserved_special_token_182|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128191": {
-      "content": "<|reserved_special_token_183|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128192": {
-      "content": "<|reserved_special_token_184|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128193": {
-      "content": "<|reserved_special_token_185|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128194": {
-      "content": "<|reserved_special_token_186|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128195": {
-      "content": "<|reserved_special_token_187|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128196": {
-      "content": "<|reserved_special_token_188|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128197": {
-      "content": "<|reserved_special_token_189|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128198": {
-      "content": "<|reserved_special_token_190|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128199": {
-      "content": "<|reserved_special_token_191|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128200": {
-      "content": "<|reserved_special_token_192|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128201": {
-      "content": "<|reserved_special_token_193|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128202": {
-      "content": "<|reserved_special_token_194|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128203": {
-      "content": "<|reserved_special_token_195|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128204": {
-      "content": "<|reserved_special_token_196|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128205": {
-      "content": "<|reserved_special_token_197|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128206": {
-      "content": "<|reserved_special_token_198|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128207": {
-      "content": "<|reserved_special_token_199|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128208": {
-      "content": "<|reserved_special_token_200|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128209": {
-      "content": "<|reserved_special_token_201|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128210": {
-      "content": "<|reserved_special_token_202|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128211": {
-      "content": "<|reserved_special_token_203|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128212": {
-      "content": "<|reserved_special_token_204|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128213": {
-      "content": "<|reserved_special_token_205|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128214": {
-      "content": "<|reserved_special_token_206|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128215": {
-      "content": "<|reserved_special_token_207|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128216": {
-      "content": "<|reserved_special_token_208|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128217": {
-      "content": "<|reserved_special_token_209|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128218": {
-      "content": "<|reserved_special_token_210|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128219": {
-      "content": "<|reserved_special_token_211|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128220": {
-      "content": "<|reserved_special_token_212|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128221": {
-      "content": "<|reserved_special_token_213|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128222": {
-      "content": "<|reserved_special_token_214|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128223": {
-      "content": "<|reserved_special_token_215|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128224": {
-      "content": "<|reserved_special_token_216|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128225": {
-      "content": "<|reserved_special_token_217|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128226": {
-      "content": "<|reserved_special_token_218|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128227": {
-      "content": "<|reserved_special_token_219|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128228": {
-      "content": "<|reserved_special_token_220|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128229": {
-      "content": "<|reserved_special_token_221|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128230": {
-      "content": "<|reserved_special_token_222|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128231": {
-      "content": "<|reserved_special_token_223|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128232": {
-      "content": "<|reserved_special_token_224|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128233": {
-      "content": "<|reserved_special_token_225|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128234": {
-      "content": "<|reserved_special_token_226|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128235": {
-      "content": "<|reserved_special_token_227|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128236": {
-      "content": "<|reserved_special_token_228|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128237": {
-      "content": "<|reserved_special_token_229|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128238": {
-      "content": "<|reserved_special_token_230|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128239": {
-      "content": "<|reserved_special_token_231|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128240": {
-      "content": "<|reserved_special_token_232|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128241": {
-      "content": "<|reserved_special_token_233|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128242": {
-      "content": "<|reserved_special_token_234|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128243": {
-      "content": "<|reserved_special_token_235|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128244": {
-      "content": "<|reserved_special_token_236|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128245": {
-      "content": "<|reserved_special_token_237|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128246": {
-      "content": "<|reserved_special_token_238|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128247": {
-      "content": "<|reserved_special_token_239|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128248": {
-      "content": "<|reserved_special_token_240|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128249": {
-      "content": "<|reserved_special_token_241|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128250": {
-      "content": "<|reserved_special_token_242|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128251": {
-      "content": "<|reserved_special_token_243|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128252": {
-      "content": "<|reserved_special_token_244|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128253": {
-      "content": "<|reserved_special_token_245|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128254": {
-      "content": "<|reserved_special_token_246|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128255": {
-      "content": "<|reserved_special_token_247|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "128256": {
-      "content": "<PAD>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "auto_map": {
-    "AutoProcessor": "processing_prismatic.PrismaticProcessor"
-  },
-  "bos_token": "<|begin_of_text|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 131072,
-  "pad_token": "<PAD>",
-  "processor_class": "PrismaticProcessor",
-  "tokenizer_class": "PreTrainedTokenizerFast"
-}