Add files using upload-large-folder tool
Browse files- config.json +17 -4
- generation_config.json +2 -3
- preprocessor_config.json +18 -8
- recipe.yaml +3 -3
- tokenizer_config.json +2 -1
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "Qwen/Qwen2.5-VL-72B-Instruct",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2_5_VLForConditionalGeneration"
|
| 5 |
],
|
|
@@ -51,7 +50,7 @@
|
|
| 51 |
}
|
| 52 |
},
|
| 53 |
"format": "float-quantized",
|
| 54 |
-
"global_compression_ratio":
|
| 55 |
"ignore": [
|
| 56 |
"visual.blocks.0.attn.qkv",
|
| 57 |
"visual.blocks.0.attn.proj",
|
|
@@ -235,18 +234,32 @@
|
|
| 235 |
"sliding_window": 32768,
|
| 236 |
"tie_word_embeddings": false,
|
| 237 |
"torch_dtype": "bfloat16",
|
| 238 |
-
"transformers_version": "4.
|
| 239 |
"use_cache": true,
|
| 240 |
"use_sliding_window": false,
|
| 241 |
"video_token_id": 151656,
|
| 242 |
"vision_config": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 243 |
"hidden_size": 1280,
|
|
|
|
| 244 |
"in_chans": 3,
|
| 245 |
"intermediate_size": 3456,
|
| 246 |
"model_type": "qwen2_5_vl",
|
|
|
|
| 247 |
"out_hidden_size": 8192,
|
|
|
|
|
|
|
| 248 |
"spatial_patch_size": 14,
|
| 249 |
-
"
|
|
|
|
|
|
|
| 250 |
},
|
| 251 |
"vision_end_token_id": 151653,
|
| 252 |
"vision_start_token_id": 151652,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
],
|
|
|
|
| 50 |
}
|
| 51 |
},
|
| 52 |
"format": "float-quantized",
|
| 53 |
+
"global_compression_ratio": null,
|
| 54 |
"ignore": [
|
| 55 |
"visual.blocks.0.attn.qkv",
|
| 56 |
"visual.blocks.0.attn.proj",
|
|
|
|
| 234 |
"sliding_window": 32768,
|
| 235 |
"tie_word_embeddings": false,
|
| 236 |
"torch_dtype": "bfloat16",
|
| 237 |
+
"transformers_version": "4.51.3",
|
| 238 |
"use_cache": true,
|
| 239 |
"use_sliding_window": false,
|
| 240 |
"video_token_id": 151656,
|
| 241 |
"vision_config": {
|
| 242 |
+
"depth": 32,
|
| 243 |
+
"fullatt_block_indexes": [
|
| 244 |
+
7,
|
| 245 |
+
15,
|
| 246 |
+
23,
|
| 247 |
+
31
|
| 248 |
+
],
|
| 249 |
+
"hidden_act": "silu",
|
| 250 |
"hidden_size": 1280,
|
| 251 |
+
"in_channels": 3,
|
| 252 |
"in_chans": 3,
|
| 253 |
"intermediate_size": 3456,
|
| 254 |
"model_type": "qwen2_5_vl",
|
| 255 |
+
"num_heads": 16,
|
| 256 |
"out_hidden_size": 8192,
|
| 257 |
+
"patch_size": 14,
|
| 258 |
+
"spatial_merge_size": 2,
|
| 259 |
"spatial_patch_size": 14,
|
| 260 |
+
"temporal_patch_size": 2,
|
| 261 |
+
"tokens_per_second": 2,
|
| 262 |
+
"window_size": 112
|
| 263 |
},
|
| 264 |
"vision_end_token_id": 151653,
|
| 265 |
"vision_start_token_id": 151652,
|
generation_config.json
CHANGED
|
@@ -7,7 +7,6 @@
|
|
| 7 |
],
|
| 8 |
"pad_token_id": 151643,
|
| 9 |
"repetition_penalty": 1.05,
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"transformers_version": "4.49.0"
|
| 13 |
}
|
|
|
|
| 7 |
],
|
| 8 |
"pad_token_id": 151643,
|
| 9 |
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 1e-06,
|
| 11 |
+
"transformers_version": "4.51.3"
|
|
|
|
| 12 |
}
|
preprocessor_config.json
CHANGED
|
@@ -1,19 +1,29 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"merge_size": 2,
|
| 7 |
"image_mean": [
|
| 8 |
0.48145466,
|
| 9 |
0.4578275,
|
| 10 |
0.40821073
|
| 11 |
],
|
|
|
|
| 12 |
"image_std": [
|
| 13 |
0.26862954,
|
| 14 |
0.26130258,
|
| 15 |
0.27577711
|
| 16 |
],
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
|
|
|
| 6 |
"image_mean": [
|
| 7 |
0.48145466,
|
| 8 |
0.4578275,
|
| 9 |
0.40821073
|
| 10 |
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
"image_std": [
|
| 13 |
0.26862954,
|
| 14 |
0.26130258,
|
| 15 |
0.27577711
|
| 16 |
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
recipe.yaml
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
QuantizationModifier:
|
| 4 |
-
ignore: [lm_head, 're:visual.*']
|
| 5 |
targets: [Linear]
|
| 6 |
scheme: FP8_DYNAMIC
|
|
|
|
| 1 |
+
default_stage:
|
| 2 |
+
default_modifiers:
|
| 3 |
QuantizationModifier:
|
| 4 |
+
ignore: ['re:.*lm_head', 're:visual.*']
|
| 5 |
targets: [Linear]
|
| 6 |
scheme: FP8_DYNAMIC
|
tokenizer_config.json
CHANGED
|
@@ -195,13 +195,14 @@
|
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
| 198 |
-
"chat_template": "{%
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"errors": "replace",
|
| 202 |
"extra_special_tokens": {},
|
| 203 |
"model_max_length": 131072,
|
| 204 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 205 |
"split_special_tokens": false,
|
| 206 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
"unk_token": null
|
|
|
|
| 195 |
"<|video_pad|>"
|
| 196 |
],
|
| 197 |
"bos_token": null,
|
| 198 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|im_end|>",
|
| 201 |
"errors": "replace",
|
| 202 |
"extra_special_tokens": {},
|
| 203 |
"model_max_length": 131072,
|
| 204 |
"pad_token": "<|endoftext|>",
|
| 205 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 206 |
"split_special_tokens": false,
|
| 207 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 208 |
"unk_token": null
|