Upload folder using huggingface_hub
Browse files- config.json +3 -3
- generation_config.json +1 -1
- model-00001-of-00007.safetensors +2 -2
- model-00002-of-00007.safetensors +2 -2
- model-00003-of-00007.safetensors +2 -2
- model-00004-of-00007.safetensors +2 -2
- model-00005-of-00007.safetensors +2 -2
- model-00006-of-00007.safetensors +2 -2
- model-00007-of-00007.safetensors +2 -2
- model.safetensors.index.json +0 -0
- processor_config.json +84 -0
- recipe.yaml +4 -0
config.json
CHANGED
|
@@ -202,7 +202,7 @@
|
|
| 202 |
"quantization_status": "compressed",
|
| 203 |
"sparsity_config": {},
|
| 204 |
"transform_config": {},
|
| 205 |
-
"version": "0.12.
|
| 206 |
},
|
| 207 |
"text_config": {
|
| 208 |
"attention_bias": false,
|
|
@@ -242,7 +242,7 @@
|
|
| 242 |
"vocab_size": 151936
|
| 243 |
},
|
| 244 |
"tie_word_embeddings": false,
|
| 245 |
-
"transformers_version": "
|
| 246 |
"video_token_id": 151656,
|
| 247 |
"vision_config": {
|
| 248 |
"deepstack_visual_indexes": [
|
|
@@ -266,4 +266,4 @@
|
|
| 266 |
},
|
| 267 |
"vision_end_token_id": 151653,
|
| 268 |
"vision_start_token_id": 151652
|
| 269 |
-
}
|
|
|
|
| 202 |
"quantization_status": "compressed",
|
| 203 |
"sparsity_config": {},
|
| 204 |
"transform_config": {},
|
| 205 |
+
"version": "0.12.3.a20251114"
|
| 206 |
},
|
| 207 |
"text_config": {
|
| 208 |
"attention_bias": false,
|
|
|
|
| 242 |
"vocab_size": 151936
|
| 243 |
},
|
| 244 |
"tie_word_embeddings": false,
|
| 245 |
+
"transformers_version": "5.0.0.dev0",
|
| 246 |
"video_token_id": 151656,
|
| 247 |
"vision_config": {
|
| 248 |
"deepstack_visual_indexes": [
|
|
|
|
| 266 |
},
|
| 267 |
"vision_end_token_id": 151653,
|
| 268 |
"vision_start_token_id": 151652
|
| 269 |
+
}
|
generation_config.json
CHANGED
|
@@ -9,5 +9,5 @@
|
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
| 12 |
-
"transformers_version": "
|
| 13 |
}
|
|
|
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "5.0.0.dev0"
|
| 13 |
}
|
model-00001-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5da92047ea282f651c46a53ee32bb5ca0bc10153d13067081600ab507e6e468d
|
| 3 |
+
size 5000333360
|
model-00002-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b3bdb7704d2ea787ef6952fd153d836b4bb96a36fee69f299ce4b972f17ba80
|
| 3 |
+
size 5000644624
|
model-00003-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e094d99587a8dc7d6543d84a0b020f422b4e614f9d57d4449929a037d7c9e54
|
| 3 |
+
size 5000650752
|
model-00004-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daf89de1ae7cdb42acda645c284fbb868a895f2425c02b89157e6e05a39843c6
|
| 3 |
+
size 5000120408
|
model-00005-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdf69ce33f1b922fb2c103c3316ad624f8bb652cabf3d1c2cdf2630e4c7060e5
|
| 3 |
+
size 5000650720
|
model-00006-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcd1dbb83a189c3a4223ac372b1e9d712199338a3412300127b7b06b62036b3b
|
| 3 |
+
size 5000120448
|
model-00007-of-00007.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0dde7f57942bfe37e4e02d72d4a57eab45ffb02348c1982309bd11b533c8cc0
|
| 3 |
+
size 4118634560
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor_config.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"crop_size": null,
|
| 4 |
+
"data_format": "channels_first",
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": null,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 16777216,
|
| 36 |
+
"shortest_edge": 65536
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
},
|
| 40 |
+
"processor_class": "Qwen3VLProcessor",
|
| 41 |
+
"video_processor": {
|
| 42 |
+
"crop_size": null,
|
| 43 |
+
"data_format": "channels_first",
|
| 44 |
+
"default_to_square": true,
|
| 45 |
+
"device": null,
|
| 46 |
+
"do_center_crop": null,
|
| 47 |
+
"do_convert_rgb": true,
|
| 48 |
+
"do_normalize": true,
|
| 49 |
+
"do_pad": null,
|
| 50 |
+
"do_rescale": true,
|
| 51 |
+
"do_resize": true,
|
| 52 |
+
"do_sample_frames": true,
|
| 53 |
+
"fps": 2,
|
| 54 |
+
"image_mean": [
|
| 55 |
+
0.5,
|
| 56 |
+
0.5,
|
| 57 |
+
0.5
|
| 58 |
+
],
|
| 59 |
+
"image_std": [
|
| 60 |
+
0.5,
|
| 61 |
+
0.5,
|
| 62 |
+
0.5
|
| 63 |
+
],
|
| 64 |
+
"input_data_format": null,
|
| 65 |
+
"max_frames": 768,
|
| 66 |
+
"merge_size": 2,
|
| 67 |
+
"min_frames": 4,
|
| 68 |
+
"num_frames": null,
|
| 69 |
+
"pad_size": null,
|
| 70 |
+
"patch_size": 16,
|
| 71 |
+
"processor_class": "Qwen3VLProcessor",
|
| 72 |
+
"resample": 3,
|
| 73 |
+
"rescale_factor": 0.00392156862745098,
|
| 74 |
+
"return_metadata": false,
|
| 75 |
+
"return_tensors": null,
|
| 76 |
+
"size": {
|
| 77 |
+
"longest_edge": 25165824,
|
| 78 |
+
"shortest_edge": 4096
|
| 79 |
+
},
|
| 80 |
+
"temporal_patch_size": 2,
|
| 81 |
+
"video_metadata": null,
|
| 82 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 83 |
+
}
|
| 84 |
+
}
|
recipe.yaml
CHANGED
|
@@ -13,6 +13,8 @@ default_stage:
|
|
| 13 |
block_structure: null
|
| 14 |
dynamic: false
|
| 15 |
actorder: null
|
|
|
|
|
|
|
| 16 |
observer: mse
|
| 17 |
observer_kwargs: {}
|
| 18 |
input_activations: null
|
|
@@ -30,4 +32,6 @@ default_stage:
|
|
| 30 |
balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
|
| 31 |
- smooth_layer: re:.*up_proj$
|
| 32 |
balance_layers: ['re:.*down_proj$']
|
|
|
|
| 33 |
duo_scaling: true
|
|
|
|
|
|
| 13 |
block_structure: null
|
| 14 |
dynamic: false
|
| 15 |
actorder: null
|
| 16 |
+
scale_dtype: null
|
| 17 |
+
zp_dtype: null
|
| 18 |
observer: mse
|
| 19 |
observer_kwargs: {}
|
| 20 |
input_activations: null
|
|
|
|
| 32 |
balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
|
| 33 |
- smooth_layer: re:.*up_proj$
|
| 34 |
balance_layers: ['re:.*down_proj$']
|
| 35 |
+
offload_device: !!python/object/apply:torch.device [cpu]
|
| 36 |
duo_scaling: true
|
| 37 |
+
n_grid: 20
|