Add files using upload-large-folder tool

README.md

@@ -0,0 +1,125 @@
+---
+license: apache-2.0
+datasets:
+- Nikity/Kyoto-Corpus
+language:
+- en
+base_model: mlx-community/lille-130m-instruct-fp16
+base_model_relation: finetune
+pipeline_tag: text-generation
+tags:
+- mlx
+library_name: mlx
+model-index:
+- name: lille-130m-instruct
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: arc_challenge
+      type: arc_challenge
+    metrics:
+    - type: Accuracy
+      value: 15.05
+      name: ARC (Challenge)
+  - task:
+      type: text-generation
+    dataset:
+      name: arc_easy
+      type: arc_easy
+    metrics:
+    - type: Accuracy
+      value: 21.4
+      name: ARC (Easy)
+  - task:
+      type: text-generation
+    dataset:
+      name: gpqa
+      type: gpqa
+    metrics:
+    - type: Accuracy
+      value: 12.73
+      name: GPQA
+  - task:
+      type: text-generation
+    dataset:
+      name: gsm8k
+      type: gsm8k
+    metrics:
+    - type: Accuracy
+      value: 7.73
+      name: GSM8K
+  - task:
+      type: text-generation
+    dataset:
+      name: ifeval
+      type: ifeval
+    metrics:
+    - type: Accuracy
+      value: 9.01
+      name: IFEVAL
+  - task:
+      type: text-generation
+    dataset:
+      name: math
+      type: math
+    metrics:
+    - type: Accuracy
+      value: 1.91
+      name: MATH (Level 5)
+  - task:
+      type: text-generation
+    dataset:
+      name: mmlu
+      type: mmlu
+    metrics:
+    - type: Accuracy
+      value: 22.76
+      name: MMLU
+  - task:
+      type: text-generation
+    dataset:
+      name: mt_bench
+      type: mt_bench
+    metrics:
+    - type: Accuracy
+      value: 8.2
+      name: MT-Bench
+  - task:
+      type: text-generation
+    dataset:
+      name: truthful_qa
+      type: truthful_qa
+    metrics:
+    - type: Accuracy
+      value: 9.06
+      name: TruthfulQA
+---
+
+# mlx-community/lille-130m-instruct-bf16
+
+This model [mlx-community/lille-130m-instruct-bf16](https://huggingface.co/mlx-community/lille-130m-instruct-bf16) was
+converted to MLX format from [mlx-community/lille-130m-instruct-fp16](https://huggingface.co/mlx-community/lille-130m-instruct-fp16)
+using mlx-lm version **0.27.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/lille-130m-instruct-bf16")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1 @@
+{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>' + message['content'] + '<|assistant|>' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,17 @@
+{
+    "architectures": [
+        "LilleForCausalLM"
+    ],
+    "block_size": 512,
+    "dropout": 0.0,
+    "layer_norm_eps": 1e-05,
+    "model_type": "lille-130m",
+    "n_embd": 640,
+    "n_head": 10,
+    "n_kv_heads": 2,
+    "n_layer": 24,
+    "rope_theta": 10000.0,
+    "torch_dtype": "float32",
+    "transformers_version": "4.53.3",
+    "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.53.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d08f443d2eb5da5671a7ffbbcf33517c81bc28c77b14b57ce90645faa042eb
+size 254362893

model.safetensors.index.json

@@ -0,0 +1,178 @@
+{
+    "metadata": {
+        "total_size": 254342400,
+        "total_parameters": 127171200
+    },
+    "weight_map": {
+        "transformer.layers.0.attention.norm.weight": "model.safetensors",
+        "transformer.layers.0.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.0.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.0.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.0.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.0.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.0.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.1.attention.norm.weight": "model.safetensors",
+        "transformer.layers.1.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.1.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.1.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.1.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.1.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.1.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.10.attention.norm.weight": "model.safetensors",
+        "transformer.layers.10.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.10.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.10.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.10.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.10.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.10.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.11.attention.norm.weight": "model.safetensors",
+        "transformer.layers.11.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.11.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.11.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.11.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.11.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.11.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.12.attention.norm.weight": "model.safetensors",
+        "transformer.layers.12.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.12.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.12.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.12.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.12.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.12.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.13.attention.norm.weight": "model.safetensors",
+        "transformer.layers.13.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.13.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.13.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.13.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.13.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.13.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.14.attention.norm.weight": "model.safetensors",
+        "transformer.layers.14.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.14.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.14.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.14.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.14.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.14.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.15.attention.norm.weight": "model.safetensors",
+        "transformer.layers.15.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.15.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.15.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.15.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.15.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.15.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.16.attention.norm.weight": "model.safetensors",
+        "transformer.layers.16.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.16.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.16.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.16.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.16.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.16.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.17.attention.norm.weight": "model.safetensors",
+        "transformer.layers.17.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.17.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.17.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.17.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.17.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.17.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.18.attention.norm.weight": "model.safetensors",
+        "transformer.layers.18.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.18.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.18.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.18.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.18.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.18.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.19.attention.norm.weight": "model.safetensors",
+        "transformer.layers.19.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.19.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.19.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.19.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.19.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.19.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.2.attention.norm.weight": "model.safetensors",
+        "transformer.layers.2.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.2.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.2.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.2.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.2.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.2.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.20.attention.norm.weight": "model.safetensors",
+        "transformer.layers.20.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.20.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.20.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.20.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.20.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.20.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.21.attention.norm.weight": "model.safetensors",
+        "transformer.layers.21.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.21.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.21.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.21.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.21.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.21.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.22.attention.norm.weight": "model.safetensors",
+        "transformer.layers.22.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.22.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.22.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.22.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.22.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.22.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.23.attention.norm.weight": "model.safetensors",
+        "transformer.layers.23.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.23.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.23.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.23.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.23.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.23.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.3.attention.norm.weight": "model.safetensors",
+        "transformer.layers.3.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.3.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.3.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.3.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.3.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.3.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.4.attention.norm.weight": "model.safetensors",
+        "transformer.layers.4.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.4.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.4.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.4.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.4.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.4.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.5.attention.norm.weight": "model.safetensors",
+        "transformer.layers.5.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.5.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.5.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.5.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.5.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.5.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.6.attention.norm.weight": "model.safetensors",
+        "transformer.layers.6.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.6.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.6.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.6.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.6.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.6.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.7.attention.norm.weight": "model.safetensors",
+        "transformer.layers.7.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.7.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.7.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.7.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.7.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.7.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.8.attention.norm.weight": "model.safetensors",
+        "transformer.layers.8.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.8.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.8.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.8.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.8.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.8.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.layers.9.attention.norm.weight": "model.safetensors",
+        "transformer.layers.9.attention.out_proj.weight": "model.safetensors",
+        "transformer.layers.9.attention.qkv_proj.weight": "model.safetensors",
+        "transformer.layers.9.feed_forward.down_proj.weight": "model.safetensors",
+        "transformer.layers.9.feed_forward.gate_proj.weight": "model.safetensors",
+        "transformer.layers.9.feed_forward.norm.weight": "model.safetensors",
+        "transformer.layers.9.feed_forward.up_proj.weight": "model.safetensors",
+        "transformer.norm.weight": "model.safetensors",
+        "transformer.tok_embeddings.weight": "model.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|assistant|>",
+    "<|user|>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "32763": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32764": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32765": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32766": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32767": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|assistant|>",
+    "<|user|>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}