Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/model_index-checkpoint.json +32 -0
- model_index.json +32 -0
- scheduler/.ipynb_checkpoints/scheduler_config-checkpoint.json +6 -0
- scheduler/scheduler_config.json +6 -0
- text_encoder/.gitattributes +35 -0
- text_encoder/.ipynb_checkpoints/config-checkpoint.json +61 -0
- text_encoder/README.md +528 -0
- text_encoder/chat_template.json +3 -0
- text_encoder/config.json +61 -0
- text_encoder/generation_config.json +12 -0
- text_encoder/model-00001-of-00005.safetensors +3 -0
- text_encoder/model-00002-of-00005.safetensors +3 -0
- text_encoder/model-00003-of-00005.safetensors +3 -0
- text_encoder/model-00004-of-00005.safetensors +3 -0
- text_encoder/model-00005-of-00005.safetensors +3 -0
- text_encoder/model.safetensors.index.json +736 -0
- text_encoder_2/.gitattributes +28 -0
- text_encoder_2/README.md +145 -0
- text_encoder_2/config.json +171 -0
- text_encoder_2/flax_model.msgpack +3 -0
- text_encoder_2/model.safetensors +3 -0
- text_encoder_2/preprocessor_config.json +19 -0
- text_encoder_2/pytorch_model.bin +3 -0
- text_encoder_2/tf_model.h5 +3 -0
- tokenizer/.ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
- tokenizer/merges.txt +0 -0
- tokenizer/preprocessor_config.json +19 -0
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer_config.json +207 -0
- tokenizer/vocab.json +0 -0
- tokenizer_2/.ipynb_checkpoints/merges-checkpoint.txt +0 -0
- tokenizer_2/merges.txt +0 -0
- tokenizer_2/special_tokens_map.json +1 -0
- tokenizer_2/tokenizer.json +0 -0
- tokenizer_2/tokenizer_config.json +34 -0
- tokenizer_2/vocab.json +0 -0
- transformer/.ipynb_checkpoints/config-checkpoint.json +37 -0
- transformer/config.json +37 -0
- transformer/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +32 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
.ipynb_checkpoints/model_index-checkpoint.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "Kandinsky5T2VPipeline",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"scheduler": [
|
| 5 |
+
"diffusers",
|
| 6 |
+
"FlowMatchEulerDiscreteScheduler"
|
| 7 |
+
],
|
| 8 |
+
"text_encoder": [
|
| 9 |
+
"transformers",
|
| 10 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 11 |
+
],
|
| 12 |
+
"tokenizer": [
|
| 13 |
+
"transformers",
|
| 14 |
+
"Qwen2VLProcessor"
|
| 15 |
+
],
|
| 16 |
+
"text_encoder_2": [
|
| 17 |
+
"transformers",
|
| 18 |
+
"CLIPTextModel"
|
| 19 |
+
],
|
| 20 |
+
"tokenizer_2": [
|
| 21 |
+
"transformers",
|
| 22 |
+
"CLIPTokenizer"
|
| 23 |
+
],
|
| 24 |
+
"transformer": [
|
| 25 |
+
"diffusers",
|
| 26 |
+
"Kandinsky5Transformer3DModel"
|
| 27 |
+
],
|
| 28 |
+
"vae": [
|
| 29 |
+
"diffusers",
|
| 30 |
+
"AutoencoderKLHunyuanVideo"
|
| 31 |
+
]
|
| 32 |
+
}
|
model_index.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "Kandinsky5T2VPipeline",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"scheduler": [
|
| 5 |
+
"diffusers",
|
| 6 |
+
"FlowMatchEulerDiscreteScheduler"
|
| 7 |
+
],
|
| 8 |
+
"text_encoder": [
|
| 9 |
+
"transformers",
|
| 10 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 11 |
+
],
|
| 12 |
+
"tokenizer": [
|
| 13 |
+
"transformers",
|
| 14 |
+
"Qwen2VLProcessor"
|
| 15 |
+
],
|
| 16 |
+
"text_encoder_2": [
|
| 17 |
+
"transformers",
|
| 18 |
+
"CLIPTextModel"
|
| 19 |
+
],
|
| 20 |
+
"tokenizer_2": [
|
| 21 |
+
"transformers",
|
| 22 |
+
"CLIPTokenizer"
|
| 23 |
+
],
|
| 24 |
+
"transformer": [
|
| 25 |
+
"diffusers",
|
| 26 |
+
"Kandinsky5Transformer3DModel"
|
| 27 |
+
],
|
| 28 |
+
"vae": [
|
| 29 |
+
"diffusers",
|
| 30 |
+
"AutoencoderKLHunyuanVideo"
|
| 31 |
+
]
|
| 32 |
+
}
|
scheduler/.ipynb_checkpoints/scheduler_config-checkpoint.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"num_train_timesteps": 1000,
|
| 5 |
+
"shift": 5.0
|
| 6 |
+
}
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "FlowMatchEulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"num_train_timesteps": 1000,
|
| 5 |
+
"shift": 5.0
|
| 6 |
+
}
|
text_encoder/.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
text_encoder/.ipynb_checkpoints/config-checkpoint.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"vision_start_token_id": 151652,
|
| 9 |
+
"vision_end_token_id": 151653,
|
| 10 |
+
"vision_token_id": 151654,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"video_token_id": 151656,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 18944,
|
| 17 |
+
"max_position_embeddings": 128000,
|
| 18 |
+
"max_window_layers": 28,
|
| 19 |
+
"model_type": "qwen2_5_vl",
|
| 20 |
+
"num_attention_heads": 28,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
+
"sliding_window": 32768,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.41.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_sliding_window": false,
|
| 31 |
+
"vision_config": {
|
| 32 |
+
"depth": 32,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 1280,
|
| 35 |
+
"intermediate_size": 3420,
|
| 36 |
+
"num_heads": 16,
|
| 37 |
+
"in_chans": 3,
|
| 38 |
+
"out_hidden_size": 3584,
|
| 39 |
+
"patch_size": 14,
|
| 40 |
+
"spatial_merge_size": 2,
|
| 41 |
+
"spatial_patch_size": 14,
|
| 42 |
+
"window_size": 112,
|
| 43 |
+
"fullatt_block_indexes": [
|
| 44 |
+
7,
|
| 45 |
+
15,
|
| 46 |
+
23,
|
| 47 |
+
31
|
| 48 |
+
],
|
| 49 |
+
"tokens_per_second": 2,
|
| 50 |
+
"temporal_patch_size": 2
|
| 51 |
+
},
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"type": "mrope",
|
| 54 |
+
"mrope_section": [
|
| 55 |
+
16,
|
| 56 |
+
24,
|
| 57 |
+
24
|
| 58 |
+
]
|
| 59 |
+
},
|
| 60 |
+
"vocab_size": 152064
|
| 61 |
+
}
|
text_encoder/README.md
ADDED
|
@@ -0,0 +1,528 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: image-text-to-text
|
| 7 |
+
tags:
|
| 8 |
+
- multimodal
|
| 9 |
+
library_name: transformers
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Qwen2.5-VL-7B-Instruct
|
| 13 |
+
<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
|
| 14 |
+
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
|
| 15 |
+
</a>
|
| 16 |
+
|
| 17 |
+
## Introduction
|
| 18 |
+
|
| 19 |
+
In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5-VL.
|
| 20 |
+
|
| 21 |
+
#### Key Enhancements:
|
| 22 |
+
* **Understand things visually**: Qwen2.5-VL is not only proficient in recognizing common objects such as flowers, birds, fish, and insects, but it is highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
|
| 23 |
+
|
| 24 |
+
* **Being agentic**: Qwen2.5-VL directly plays as a visual agent that can reason and dynamically direct tools, which is capable of computer use and phone use.
|
| 25 |
+
|
| 26 |
+
* **Understanding long videos and capturing events**: Qwen2.5-VL can comprehend videos of over 1 hour, and this time it has a new ability of cpaturing event by pinpointing the relevant video segments.
|
| 27 |
+
|
| 28 |
+
* **Capable of visual localization in different formats**: Qwen2.5-VL can accurately localize objects in an image by generating bounding boxes or points, and it can provide stable JSON outputs for coordinates and attributes.
|
| 29 |
+
|
| 30 |
+
* **Generating structured outputs**: for data like scans of invoices, forms, tables, etc. Qwen2.5-VL supports structured outputs of their contents, benefiting usages in finance, commerce, etc.
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
#### Model Architecture Updates:
|
| 34 |
+
|
| 35 |
+
* **Dynamic Resolution and Frame Rate Training for Video Understanding**:
|
| 36 |
+
|
| 37 |
+
We extend dynamic resolution to the temporal dimension by adopting dynamic FPS sampling, enabling the model to comprehend videos at various sampling rates. Accordingly, we update mRoPE in the time dimension with IDs and absolute time alignment, enabling the model to learn temporal sequence and speed, and ultimately acquire the ability to pinpoint specific moments.
|
| 38 |
+
|
| 39 |
+
<p align="center">
|
| 40 |
+
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-VL/qwen2.5vl_arc.jpeg" width="80%"/>
|
| 41 |
+
<p>
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
* **Streamlined and Efficient Vision Encoder**
|
| 45 |
+
|
| 46 |
+
We enhance both training and inference speeds by strategically implementing window attention into the ViT. The ViT architecture is further optimized with SwiGLU and RMSNorm, aligning it with the structure of the Qwen2.5 LLM.
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
We have three models with 3, 7 and 72 billion parameters. This repo contains the instruction-tuned 7B Qwen2.5-VL model. For more information, visit our [Blog](https://qwenlm.github.io/blog/qwen2.5-vl/) and [GitHub](https://github.com/QwenLM/Qwen2.5-VL).
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
## Evaluation
|
| 54 |
+
|
| 55 |
+
### Image benchmark
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
| Benchmark | InternVL2.5-8B | MiniCPM-o 2.6 | GPT-4o-mini | Qwen2-VL-7B |**Qwen2.5-VL-7B** |
|
| 59 |
+
| :--- | :---: | :---: | :---: | :---: | :---: |
|
| 60 |
+
| MMMU<sub>val</sub> | 56 | 50.4 | **60**| 54.1 | 58.6|
|
| 61 |
+
| MMMU-Pro<sub>val</sub> | 34.3 | - | 37.6| 30.5 | 41.0|
|
| 62 |
+
| DocVQA<sub>test</sub> | 93 | 93 | - | 94.5 | **95.7** |
|
| 63 |
+
| InfoVQA<sub>test</sub> | 77.6 | - | - |76.5 | **82.6** |
|
| 64 |
+
| ChartQA<sub>test</sub> | 84.8 | - |- | 83.0 |**87.3** |
|
| 65 |
+
| TextVQA<sub>val</sub> | 79.1 | 80.1 | -| 84.3 | **84.9**|
|
| 66 |
+
| OCRBench | 822 | 852 | 785 | 845 | **864** |
|
| 67 |
+
| CC_OCR | 57.7 | | | 61.6 | **77.8**|
|
| 68 |
+
| MMStar | 62.8| | |60.7| **63.9**|
|
| 69 |
+
| MMBench-V1.1-En<sub>test</sub> | 79.4 | 78.0 | 76.0| 80.7 | **82.6** |
|
| 70 |
+
| MMT-Bench<sub>test</sub> | - | - | - |**63.7** |63.6 |
|
| 71 |
+
| MMStar | **61.5** | 57.5 | 54.8 | 60.7 |63.9 |
|
| 72 |
+
| MMVet<sub>GPT-4-Turbo</sub> | 54.2 | 60.0 | 66.9 | 62.0 | **67.1**|
|
| 73 |
+
| HallBench<sub>avg</sub> | 45.2 | 48.1 | 46.1| 50.6 | **52.9**|
|
| 74 |
+
| MathVista<sub>testmini</sub> | 58.3 | 60.6 | 52.4 | 58.2 | **68.2**|
|
| 75 |
+
| MathVision | - | - | - | 16.3 | **25.07** |
|
| 76 |
+
|
| 77 |
+
### Video Benchmarks
|
| 78 |
+
|
| 79 |
+
| Benchmark | Qwen2-VL-7B | **Qwen2.5-VL-7B** |
|
| 80 |
+
| :--- | :---: | :---: |
|
| 81 |
+
| MVBench | 67.0 | **69.6** |
|
| 82 |
+
| PerceptionTest<sub>test</sub> | 66.9 | **70.5** |
|
| 83 |
+
| Video-MME<sub>wo/w subs</sub> | 63.3/69.0 | **65.1**/**71.6** |
|
| 84 |
+
| LVBench | | 45.3 |
|
| 85 |
+
| LongVideoBench | | 54.7 |
|
| 86 |
+
| MMBench-Video | 1.44 | 1.79 |
|
| 87 |
+
| TempCompass | | 71.7 |
|
| 88 |
+
| MLVU | | 70.2 |
|
| 89 |
+
| CharadesSTA/mIoU | 43.6|
|
| 90 |
+
|
| 91 |
+
### Agent benchmark
|
| 92 |
+
| Benchmarks | Qwen2.5-VL-7B |
|
| 93 |
+
|-------------------------|---------------|
|
| 94 |
+
| ScreenSpot | 84.7 |
|
| 95 |
+
| ScreenSpot Pro | 29.0 |
|
| 96 |
+
| AITZ_EM | 81.9 |
|
| 97 |
+
| Android Control High_EM | 60.1 |
|
| 98 |
+
| Android Control Low_EM | 93.7 |
|
| 99 |
+
| AndroidWorld_SR | 25.5 |
|
| 100 |
+
| MobileMiniWob++_SR | 91.4 |
|
| 101 |
+
|
| 102 |
+
## Requirements
|
| 103 |
+
The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command:
|
| 104 |
+
```
|
| 105 |
+
pip install git+https://github.com/huggingface/transformers accelerate
|
| 106 |
+
```
|
| 107 |
+
or you might encounter the following error:
|
| 108 |
+
```
|
| 109 |
+
KeyError: 'qwen2_5_vl'
|
| 110 |
+
```
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
## Quickstart
|
| 114 |
+
|
| 115 |
+
Below, we provide simple examples to show how to use Qwen2.5-VL with 🤖 ModelScope and 🤗 Transformers.
|
| 116 |
+
|
| 117 |
+
The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command:
|
| 118 |
+
```
|
| 119 |
+
pip install git+https://github.com/huggingface/transformers accelerate
|
| 120 |
+
```
|
| 121 |
+
or you might encounter the following error:
|
| 122 |
+
```
|
| 123 |
+
KeyError: 'qwen2_5_vl'
|
| 124 |
+
```
|
| 125 |
+
|
| 126 |
+
|
| 127 |
+
We offer a toolkit to help you handle various types of visual input more conveniently, as if you were using an API. This includes base64, URLs, and interleaved images and videos. You can install it using the following command:
|
| 128 |
+
|
| 129 |
+
```bash
|
| 130 |
+
# It's highly recommanded to use `[decord]` feature for faster video loading.
|
| 131 |
+
pip install qwen-vl-utils[decord]==0.0.8
|
| 132 |
+
```
|
| 133 |
+
|
| 134 |
+
If you are not using Linux, you might not be able to install `decord` from PyPI. In that case, you can use `pip install qwen-vl-utils` which will fall back to using torchvision for video processing. However, you can still [install decord from source](https://github.com/dmlc/decord?tab=readme-ov-file#install-from-source) to get decord used when loading video.
|
| 135 |
+
|
| 136 |
+
### Using 🤗 Transformers to Chat
|
| 137 |
+
|
| 138 |
+
Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`:
|
| 139 |
+
|
| 140 |
+
```python
|
| 141 |
+
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|
| 142 |
+
from qwen_vl_utils import process_vision_info
|
| 143 |
+
|
| 144 |
+
# default: Load the model on the available device(s)
|
| 145 |
+
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
| 146 |
+
"Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
|
| 147 |
+
)
|
| 148 |
+
|
| 149 |
+
# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
|
| 150 |
+
# model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
| 151 |
+
# "Qwen/Qwen2.5-VL-7B-Instruct",
|
| 152 |
+
# torch_dtype=torch.bfloat16,
|
| 153 |
+
# attn_implementation="flash_attention_2",
|
| 154 |
+
# device_map="auto",
|
| 155 |
+
# )
|
| 156 |
+
|
| 157 |
+
# default processer
|
| 158 |
+
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
|
| 159 |
+
|
| 160 |
+
# The default range for the number of visual tokens per image in the model is 4-16384.
|
| 161 |
+
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
|
| 162 |
+
# min_pixels = 256*28*28
|
| 163 |
+
# max_pixels = 1280*28*28
|
| 164 |
+
# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
|
| 165 |
+
|
| 166 |
+
messages = [
|
| 167 |
+
{
|
| 168 |
+
"role": "user",
|
| 169 |
+
"content": [
|
| 170 |
+
{
|
| 171 |
+
"type": "image",
|
| 172 |
+
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
| 173 |
+
},
|
| 174 |
+
{"type": "text", "text": "Describe this image."},
|
| 175 |
+
],
|
| 176 |
+
}
|
| 177 |
+
]
|
| 178 |
+
|
| 179 |
+
# Preparation for inference
|
| 180 |
+
text = processor.apply_chat_template(
|
| 181 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 182 |
+
)
|
| 183 |
+
image_inputs, video_inputs = process_vision_info(messages)
|
| 184 |
+
inputs = processor(
|
| 185 |
+
text=[text],
|
| 186 |
+
images=image_inputs,
|
| 187 |
+
videos=video_inputs,
|
| 188 |
+
padding=True,
|
| 189 |
+
return_tensors="pt",
|
| 190 |
+
)
|
| 191 |
+
inputs = inputs.to("cuda")
|
| 192 |
+
|
| 193 |
+
# Inference: Generation of the output
|
| 194 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 195 |
+
generated_ids_trimmed = [
|
| 196 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 197 |
+
]
|
| 198 |
+
output_text = processor.batch_decode(
|
| 199 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 200 |
+
)
|
| 201 |
+
print(output_text)
|
| 202 |
+
```
|
| 203 |
+
<details>
|
| 204 |
+
<summary>Multi image inference</summary>
|
| 205 |
+
|
| 206 |
+
```python
|
| 207 |
+
# Messages containing multiple images and a text query
|
| 208 |
+
messages = [
|
| 209 |
+
{
|
| 210 |
+
"role": "user",
|
| 211 |
+
"content": [
|
| 212 |
+
{"type": "image", "image": "file:///path/to/image1.jpg"},
|
| 213 |
+
{"type": "image", "image": "file:///path/to/image2.jpg"},
|
| 214 |
+
{"type": "text", "text": "Identify the similarities between these images."},
|
| 215 |
+
],
|
| 216 |
+
}
|
| 217 |
+
]
|
| 218 |
+
|
| 219 |
+
# Preparation for inference
|
| 220 |
+
text = processor.apply_chat_template(
|
| 221 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 222 |
+
)
|
| 223 |
+
image_inputs, video_inputs = process_vision_info(messages)
|
| 224 |
+
inputs = processor(
|
| 225 |
+
text=[text],
|
| 226 |
+
images=image_inputs,
|
| 227 |
+
videos=video_inputs,
|
| 228 |
+
padding=True,
|
| 229 |
+
return_tensors="pt",
|
| 230 |
+
)
|
| 231 |
+
inputs = inputs.to("cuda")
|
| 232 |
+
|
| 233 |
+
# Inference
|
| 234 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 235 |
+
generated_ids_trimmed = [
|
| 236 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 237 |
+
]
|
| 238 |
+
output_text = processor.batch_decode(
|
| 239 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 240 |
+
)
|
| 241 |
+
print(output_text)
|
| 242 |
+
```
|
| 243 |
+
</details>
|
| 244 |
+
|
| 245 |
+
<details>
|
| 246 |
+
<summary>Video inference</summary>
|
| 247 |
+
|
| 248 |
+
```python
|
| 249 |
+
# Messages containing a images list as a video and a text query
|
| 250 |
+
messages = [
|
| 251 |
+
{
|
| 252 |
+
"role": "user",
|
| 253 |
+
"content": [
|
| 254 |
+
{
|
| 255 |
+
"type": "video",
|
| 256 |
+
"video": [
|
| 257 |
+
"file:///path/to/frame1.jpg",
|
| 258 |
+
"file:///path/to/frame2.jpg",
|
| 259 |
+
"file:///path/to/frame3.jpg",
|
| 260 |
+
"file:///path/to/frame4.jpg",
|
| 261 |
+
],
|
| 262 |
+
},
|
| 263 |
+
{"type": "text", "text": "Describe this video."},
|
| 264 |
+
],
|
| 265 |
+
}
|
| 266 |
+
]
|
| 267 |
+
|
| 268 |
+
# Messages containing a local video path and a text query
|
| 269 |
+
messages = [
|
| 270 |
+
{
|
| 271 |
+
"role": "user",
|
| 272 |
+
"content": [
|
| 273 |
+
{
|
| 274 |
+
"type": "video",
|
| 275 |
+
"video": "file:///path/to/video1.mp4",
|
| 276 |
+
"max_pixels": 360 * 420,
|
| 277 |
+
"fps": 1.0,
|
| 278 |
+
},
|
| 279 |
+
{"type": "text", "text": "Describe this video."},
|
| 280 |
+
],
|
| 281 |
+
}
|
| 282 |
+
]
|
| 283 |
+
|
| 284 |
+
# Messages containing a video url and a text query
|
| 285 |
+
messages = [
|
| 286 |
+
{
|
| 287 |
+
"role": "user",
|
| 288 |
+
"content": [
|
| 289 |
+
{
|
| 290 |
+
"type": "video",
|
| 291 |
+
"video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/space_woaudio.mp4",
|
| 292 |
+
},
|
| 293 |
+
{"type": "text", "text": "Describe this video."},
|
| 294 |
+
],
|
| 295 |
+
}
|
| 296 |
+
]
|
| 297 |
+
|
| 298 |
+
#In Qwen 2.5 VL, frame rate information is also input into the model to align with absolute time.
|
| 299 |
+
# Preparation for inference
|
| 300 |
+
text = processor.apply_chat_template(
|
| 301 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 302 |
+
)
|
| 303 |
+
image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True)
|
| 304 |
+
inputs = processor(
|
| 305 |
+
text=[text],
|
| 306 |
+
images=image_inputs,
|
| 307 |
+
videos=video_inputs,
|
| 308 |
+
fps=fps,
|
| 309 |
+
padding=True,
|
| 310 |
+
return_tensors="pt",
|
| 311 |
+
**video_kwargs,
|
| 312 |
+
)
|
| 313 |
+
inputs = inputs.to("cuda")
|
| 314 |
+
|
| 315 |
+
# Inference
|
| 316 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 317 |
+
generated_ids_trimmed = [
|
| 318 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 319 |
+
]
|
| 320 |
+
output_text = processor.batch_decode(
|
| 321 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 322 |
+
)
|
| 323 |
+
print(output_text)
|
| 324 |
+
```
|
| 325 |
+
|
| 326 |
+
Video URL compatibility largely depends on the third-party library version. The details are in the table below. change the backend by `FORCE_QWENVL_VIDEO_READER=torchvision` or `FORCE_QWENVL_VIDEO_READER=decord` if you prefer not to use the default one.
|
| 327 |
+
|
| 328 |
+
| Backend | HTTP | HTTPS |
|
| 329 |
+
|-------------|------|-------|
|
| 330 |
+
| torchvision >= 0.19.0 | ✅ | ✅ |
|
| 331 |
+
| torchvision < 0.19.0 | ❌ | ❌ |
|
| 332 |
+
| decord | ✅ | ❌ |
|
| 333 |
+
</details>
|
| 334 |
+
|
| 335 |
+
<details>
|
| 336 |
+
<summary>Batch inference</summary>
|
| 337 |
+
|
| 338 |
+
```python
|
| 339 |
+
# Sample messages for batch inference
|
| 340 |
+
messages1 = [
|
| 341 |
+
{
|
| 342 |
+
"role": "user",
|
| 343 |
+
"content": [
|
| 344 |
+
{"type": "image", "image": "file:///path/to/image1.jpg"},
|
| 345 |
+
{"type": "image", "image": "file:///path/to/image2.jpg"},
|
| 346 |
+
{"type": "text", "text": "What are the common elements in these pictures?"},
|
| 347 |
+
],
|
| 348 |
+
}
|
| 349 |
+
]
|
| 350 |
+
messages2 = [
|
| 351 |
+
{"role": "system", "content": "You are a helpful assistant."},
|
| 352 |
+
{"role": "user", "content": "Who are you?"},
|
| 353 |
+
]
|
| 354 |
+
# Combine messages for batch processing
|
| 355 |
+
messages = [messages1, messages2]
|
| 356 |
+
|
| 357 |
+
# Preparation for batch inference
|
| 358 |
+
texts = [
|
| 359 |
+
processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True)
|
| 360 |
+
for msg in messages
|
| 361 |
+
]
|
| 362 |
+
image_inputs, video_inputs = process_vision_info(messages)
|
| 363 |
+
inputs = processor(
|
| 364 |
+
text=texts,
|
| 365 |
+
images=image_inputs,
|
| 366 |
+
videos=video_inputs,
|
| 367 |
+
padding=True,
|
| 368 |
+
return_tensors="pt",
|
| 369 |
+
)
|
| 370 |
+
inputs = inputs.to("cuda")
|
| 371 |
+
|
| 372 |
+
# Batch Inference
|
| 373 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 374 |
+
generated_ids_trimmed = [
|
| 375 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 376 |
+
]
|
| 377 |
+
output_texts = processor.batch_decode(
|
| 378 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 379 |
+
)
|
| 380 |
+
print(output_texts)
|
| 381 |
+
```
|
| 382 |
+
</details>
|
| 383 |
+
|
| 384 |
+
### 🤖 ModelScope
|
| 385 |
+
We strongly advise users especially those in mainland China to use ModelScope. `snapshot_download` can help you solve issues concerning downloading checkpoints.
|
| 386 |
+
|
| 387 |
+
|
| 388 |
+
### More Usage Tips
|
| 389 |
+
|
| 390 |
+
For input images, we support local files, base64, and URLs. For videos, we currently only support local files.
|
| 391 |
+
|
| 392 |
+
```python
|
| 393 |
+
# You can directly insert a local file path, a URL, or a base64-encoded image into the position where you want in the text.
|
| 394 |
+
## Local file path
|
| 395 |
+
messages = [
|
| 396 |
+
{
|
| 397 |
+
"role": "user",
|
| 398 |
+
"content": [
|
| 399 |
+
{"type": "image", "image": "file:///path/to/your/image.jpg"},
|
| 400 |
+
{"type": "text", "text": "Describe this image."},
|
| 401 |
+
],
|
| 402 |
+
}
|
| 403 |
+
]
|
| 404 |
+
## Image URL
|
| 405 |
+
messages = [
|
| 406 |
+
{
|
| 407 |
+
"role": "user",
|
| 408 |
+
"content": [
|
| 409 |
+
{"type": "image", "image": "http://path/to/your/image.jpg"},
|
| 410 |
+
{"type": "text", "text": "Describe this image."},
|
| 411 |
+
],
|
| 412 |
+
}
|
| 413 |
+
]
|
| 414 |
+
## Base64 encoded image
|
| 415 |
+
messages = [
|
| 416 |
+
{
|
| 417 |
+
"role": "user",
|
| 418 |
+
"content": [
|
| 419 |
+
{"type": "image", "image": "data:image;base64,/9j/..."},
|
| 420 |
+
{"type": "text", "text": "Describe this image."},
|
| 421 |
+
],
|
| 422 |
+
}
|
| 423 |
+
]
|
| 424 |
+
```
|
| 425 |
+
#### Image Resolution for performance boost
|
| 426 |
+
|
| 427 |
+
The model supports a wide range of resolution inputs. By default, it uses the native resolution for input, but higher resolutions can enhance performance at the cost of more computation. Users can set the minimum and maximum number of pixels to achieve an optimal configuration for their needs, such as a token count range of 256-1280, to balance speed and memory usage.
|
| 428 |
+
|
| 429 |
+
```python
|
| 430 |
+
min_pixels = 256 * 28 * 28
|
| 431 |
+
max_pixels = 1280 * 28 * 28
|
| 432 |
+
processor = AutoProcessor.from_pretrained(
|
| 433 |
+
"Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels
|
| 434 |
+
)
|
| 435 |
+
```
|
| 436 |
+
|
| 437 |
+
Besides, We provide two methods for fine-grained control over the image size input to the model:
|
| 438 |
+
|
| 439 |
+
1. Define min_pixels and max_pixels: Images will be resized to maintain their aspect ratio within the range of min_pixels and max_pixels.
|
| 440 |
+
|
| 441 |
+
2. Specify exact dimensions: Directly set `resized_height` and `resized_width`. These values will be rounded to the nearest multiple of 28.
|
| 442 |
+
|
| 443 |
+
```python
|
| 444 |
+
# min_pixels and max_pixels
|
| 445 |
+
messages = [
|
| 446 |
+
{
|
| 447 |
+
"role": "user",
|
| 448 |
+
"content": [
|
| 449 |
+
{
|
| 450 |
+
"type": "image",
|
| 451 |
+
"image": "file:///path/to/your/image.jpg",
|
| 452 |
+
"resized_height": 280,
|
| 453 |
+
"resized_width": 420,
|
| 454 |
+
},
|
| 455 |
+
{"type": "text", "text": "Describe this image."},
|
| 456 |
+
],
|
| 457 |
+
}
|
| 458 |
+
]
|
| 459 |
+
# resized_height and resized_width
|
| 460 |
+
messages = [
|
| 461 |
+
{
|
| 462 |
+
"role": "user",
|
| 463 |
+
"content": [
|
| 464 |
+
{
|
| 465 |
+
"type": "image",
|
| 466 |
+
"image": "file:///path/to/your/image.jpg",
|
| 467 |
+
"min_pixels": 50176,
|
| 468 |
+
"max_pixels": 50176,
|
| 469 |
+
},
|
| 470 |
+
{"type": "text", "text": "Describe this image."},
|
| 471 |
+
],
|
| 472 |
+
}
|
| 473 |
+
]
|
| 474 |
+
```
|
| 475 |
+
|
| 476 |
+
### Processing Long Texts
|
| 477 |
+
|
| 478 |
+
The current `config.json` is set for context length up to 32,768 tokens.
|
| 479 |
+
To handle extensive inputs exceeding 32,768 tokens, we utilize [YaRN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
|
| 480 |
+
|
| 481 |
+
For supported frameworks, you could add the following to `config.json` to enable YaRN:
|
| 482 |
+
|
| 483 |
+
{
|
| 484 |
+
...,
|
| 485 |
+
"type": "yarn",
|
| 486 |
+
"mrope_section": [
|
| 487 |
+
16,
|
| 488 |
+
24,
|
| 489 |
+
24
|
| 490 |
+
],
|
| 491 |
+
"factor": 4,
|
| 492 |
+
"original_max_position_embeddings": 32768
|
| 493 |
+
}
|
| 494 |
+
|
| 495 |
+
However, it should be noted that this method has a significant impact on the performance of temporal and spatial localization tasks, and is therefore not recommended for use.
|
| 496 |
+
|
| 497 |
+
At the same time, for long video inputs, since MRoPE itself is more economical with ids, the max_position_embeddings can be directly modified to a larger value, such as 64k.
|
| 498 |
+
|
| 499 |
+
|
| 500 |
+
|
| 501 |
+
|
| 502 |
+
## Citation
|
| 503 |
+
|
| 504 |
+
If you find our work helpful, feel free to give us a cite.
|
| 505 |
+
|
| 506 |
+
```
|
| 507 |
+
@misc{qwen2.5-VL,
|
| 508 |
+
title = {Qwen2.5-VL},
|
| 509 |
+
url = {https://qwenlm.github.io/blog/qwen2.5-vl/},
|
| 510 |
+
author = {Qwen Team},
|
| 511 |
+
month = {January},
|
| 512 |
+
year = {2025}
|
| 513 |
+
}
|
| 514 |
+
|
| 515 |
+
@article{Qwen2VL,
|
| 516 |
+
title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
|
| 517 |
+
author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang},
|
| 518 |
+
journal={arXiv preprint arXiv:2409.12191},
|
| 519 |
+
year={2024}
|
| 520 |
+
}
|
| 521 |
+
|
| 522 |
+
@article{Qwen-VL,
|
| 523 |
+
title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
|
| 524 |
+
author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
|
| 525 |
+
journal={arXiv preprint arXiv:2308.12966},
|
| 526 |
+
year={2023}
|
| 527 |
+
}
|
| 528 |
+
```
|
text_encoder/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"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 %}"
|
| 3 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"vision_start_token_id": 151652,
|
| 9 |
+
"vision_end_token_id": 151653,
|
| 10 |
+
"vision_token_id": 151654,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"video_token_id": 151656,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 3584,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 18944,
|
| 17 |
+
"max_position_embeddings": 128000,
|
| 18 |
+
"max_window_layers": 28,
|
| 19 |
+
"model_type": "qwen2_5_vl",
|
| 20 |
+
"num_attention_heads": 28,
|
| 21 |
+
"num_hidden_layers": 28,
|
| 22 |
+
"num_key_value_heads": 4,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
+
"sliding_window": 32768,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.41.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_sliding_window": false,
|
| 31 |
+
"vision_config": {
|
| 32 |
+
"depth": 32,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 1280,
|
| 35 |
+
"intermediate_size": 3420,
|
| 36 |
+
"num_heads": 16,
|
| 37 |
+
"in_chans": 3,
|
| 38 |
+
"out_hidden_size": 3584,
|
| 39 |
+
"patch_size": 14,
|
| 40 |
+
"spatial_merge_size": 2,
|
| 41 |
+
"spatial_patch_size": 14,
|
| 42 |
+
"window_size": 112,
|
| 43 |
+
"fullatt_block_indexes": [
|
| 44 |
+
7,
|
| 45 |
+
15,
|
| 46 |
+
23,
|
| 47 |
+
31
|
| 48 |
+
],
|
| 49 |
+
"tokens_per_second": 2,
|
| 50 |
+
"temporal_patch_size": 2
|
| 51 |
+
},
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"type": "mrope",
|
| 54 |
+
"mrope_section": [
|
| 55 |
+
16,
|
| 56 |
+
24,
|
| 57 |
+
24
|
| 58 |
+
]
|
| 59 |
+
},
|
| 60 |
+
"vocab_size": 152064
|
| 61 |
+
}
|
text_encoder/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.000001,
|
| 11 |
+
"transformers_version": "4.37.0"
|
| 12 |
+
}
|
text_encoder/model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e97b877e47fde53a6c6e77aafb36e58e91ee9d95c4a3eeac6f1b5c0e6a1c986e
|
| 3 |
+
size 3900233256
|
text_encoder/model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9a300a43b4724eee2abe7c18ceb26768d0ab011eb0cad19d9bfd2476a24d024
|
| 3 |
+
size 3864726320
|
text_encoder/model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:111223d173e00bbee81cba1216fad28668df3476706b7fd26f4d5b50f8b3a507
|
| 3 |
+
size 3864726424
|
text_encoder/model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef47f634fa57d46ee134edcc09f34085a47da1e16c12a2abe0d67118be6d72ed
|
| 3 |
+
size 3864733680
|
text_encoder/model-00005-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c859795ad3a627a9b95bcb762e059d5b768a4a36fdd4affeff269d93fdecc67
|
| 3 |
+
size 1089994880
|
text_encoder/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,736 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 16584333312
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00005-of-00005.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00004-of-00005.safetensors",
|
| 345 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 346 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 347 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 348 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 349 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 350 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 351 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 352 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 353 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 354 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 355 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00005.safetensors",
|
| 356 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00005.safetensors",
|
| 357 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 358 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 359 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 360 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 361 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 362 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 363 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 364 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 365 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 366 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 367 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00005.safetensors",
|
| 368 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00005.safetensors",
|
| 369 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 370 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 371 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 372 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 373 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 374 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 375 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 376 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 377 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 378 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 379 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00005.safetensors",
|
| 380 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00005.safetensors",
|
| 381 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 382 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 383 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 384 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 385 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 386 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 387 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 388 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 389 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 390 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 391 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00005.safetensors",
|
| 392 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00005.safetensors",
|
| 393 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 394 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 395 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 396 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 397 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 398 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 399 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 400 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 401 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 402 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 403 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00005.safetensors",
|
| 404 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00005.safetensors",
|
| 405 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 406 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 407 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 408 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 409 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 410 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 411 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 412 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 413 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 414 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 415 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00005.safetensors",
|
| 416 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00005.safetensors",
|
| 417 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 418 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 419 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 420 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 421 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 422 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 423 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 424 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 425 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 426 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 427 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00005.safetensors",
|
| 428 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00005.safetensors",
|
| 429 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 430 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 431 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 432 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 433 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 434 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 435 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 436 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 437 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 438 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 439 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00005.safetensors",
|
| 440 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00005.safetensors",
|
| 441 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 442 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 443 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 444 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 445 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 446 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 447 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 448 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 449 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 450 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 451 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00005.safetensors",
|
| 452 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00005.safetensors",
|
| 453 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 454 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 455 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 456 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 457 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 458 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 459 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 460 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 461 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 462 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 463 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00005.safetensors",
|
| 464 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00005.safetensors",
|
| 465 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 466 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 467 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 468 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 469 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 470 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 471 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 472 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 473 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 474 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 475 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00005.safetensors",
|
| 476 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00005.safetensors",
|
| 477 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 478 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 479 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 480 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 481 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 482 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 483 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 484 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 485 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 486 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 487 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00005.safetensors",
|
| 488 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00005.safetensors",
|
| 489 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 490 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 491 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 492 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 493 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 494 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 495 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 496 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 497 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 498 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 499 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00005.safetensors",
|
| 500 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00005.safetensors",
|
| 501 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 502 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 503 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 504 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 505 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 506 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 507 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 508 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 509 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 510 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 511 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00005.safetensors",
|
| 512 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00005.safetensors",
|
| 513 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 514 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 515 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 516 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 517 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 518 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 519 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 520 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 521 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 522 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 523 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00005.safetensors",
|
| 524 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00005.safetensors",
|
| 525 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 526 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 527 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 528 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 529 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 530 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 531 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 532 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 533 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 534 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 535 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00005.safetensors",
|
| 536 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00005.safetensors",
|
| 537 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 538 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 539 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 540 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 541 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 542 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 543 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 544 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 545 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 546 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 547 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00005.safetensors",
|
| 548 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00005.safetensors",
|
| 549 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 550 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 551 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 552 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 553 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 554 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 555 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 556 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 557 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 558 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 559 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00005.safetensors",
|
| 560 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00005.safetensors",
|
| 561 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 562 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 563 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 564 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 565 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 566 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 567 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 568 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 569 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 570 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 571 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00005.safetensors",
|
| 572 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00005.safetensors",
|
| 573 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 574 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 575 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 576 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 577 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 578 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 579 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 580 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 581 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 582 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 583 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00005.safetensors",
|
| 584 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00005.safetensors",
|
| 585 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 586 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 587 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 588 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 589 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 590 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 591 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 592 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 593 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 594 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 595 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00005.safetensors",
|
| 596 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00005.safetensors",
|
| 597 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 598 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 599 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 600 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 601 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 602 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 603 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 604 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 605 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 606 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 607 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00005.safetensors",
|
| 608 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00005.safetensors",
|
| 609 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 610 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 611 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 612 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 613 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 614 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 615 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 616 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 617 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 618 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 619 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00005.safetensors",
|
| 620 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00005.safetensors",
|
| 621 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 622 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 623 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 624 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 625 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 626 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 627 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 628 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 629 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 630 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 631 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00005.safetensors",
|
| 632 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00005.safetensors",
|
| 633 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 634 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 635 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 636 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 637 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 638 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 639 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 640 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 641 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 642 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 643 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00005.safetensors",
|
| 644 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00005.safetensors",
|
| 645 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 646 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 647 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 648 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 649 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 650 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 651 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 652 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 653 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 654 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 655 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00005.safetensors",
|
| 656 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00005.safetensors",
|
| 657 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 658 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 659 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 660 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 661 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 662 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 663 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 664 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 665 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 666 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 667 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00005.safetensors",
|
| 668 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00005.safetensors",
|
| 669 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 670 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 671 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 672 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 673 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 674 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 675 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 676 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 677 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 678 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 679 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00005.safetensors",
|
| 680 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00005.safetensors",
|
| 681 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 682 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 683 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 684 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 685 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 686 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 687 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 688 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 689 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 690 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 691 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00005.safetensors",
|
| 692 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00005.safetensors",
|
| 693 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 694 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 695 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 696 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 697 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 698 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 699 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 700 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 701 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 702 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 703 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00005.safetensors",
|
| 704 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00005.safetensors",
|
| 705 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 706 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 707 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 708 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 709 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 710 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 711 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 712 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 713 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 714 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 715 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00005.safetensors",
|
| 716 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00005.safetensors",
|
| 717 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00005.safetensors",
|
| 718 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors",
|
| 719 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
| 720 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
| 721 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
| 722 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
| 723 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
| 724 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
| 725 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
| 726 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
| 727 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00005.safetensors",
|
| 728 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00005.safetensors",
|
| 729 |
+
"visual.merger.ln_q.weight": "model-00001-of-00005.safetensors",
|
| 730 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00005.safetensors",
|
| 731 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00005.safetensors",
|
| 732 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00005.safetensors",
|
| 733 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00005.safetensors",
|
| 734 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00005.safetensors"
|
| 735 |
+
}
|
| 736 |
+
}
|
text_encoder_2/.gitattributes
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
text_encoder_2/README.md
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- vision
|
| 4 |
+
widget:
|
| 5 |
+
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
|
| 6 |
+
candidate_labels: playing music, playing sports
|
| 7 |
+
example_title: Cat & Dog
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Model Card: CLIP
|
| 11 |
+
|
| 12 |
+
Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found [here](https://github.com/openai/CLIP/blob/main/model-card.md).
|
| 13 |
+
|
| 14 |
+
## Model Details
|
| 15 |
+
|
| 16 |
+
The CLIP model was developed by researchers at OpenAI to learn about what contributes to robustness in computer vision tasks. The model was also developed to test the ability of models to generalize to arbitrary image classification tasks in a zero-shot manner. It was not developed for general model deployment - to deploy models like CLIP, researchers will first need to carefully study their capabilities in relation to the specific context they’re being deployed within.
|
| 17 |
+
|
| 18 |
+
### Model Date
|
| 19 |
+
|
| 20 |
+
January 2021
|
| 21 |
+
|
| 22 |
+
### Model Type
|
| 23 |
+
|
| 24 |
+
The base model uses a ViT-L/14 Transformer architecture as an image encoder and uses a masked self-attention Transformer as a text encoder. These encoders are trained to maximize the similarity of (image, text) pairs via a contrastive loss.
|
| 25 |
+
|
| 26 |
+
The original implementation had two variants: one using a ResNet image encoder and the other using a Vision Transformer. This repository has the variant with the Vision Transformer.
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
### Documents
|
| 30 |
+
|
| 31 |
+
- [Blog Post](https://openai.com/blog/clip/)
|
| 32 |
+
- [CLIP Paper](https://arxiv.org/abs/2103.00020)
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
### Use with Transformers
|
| 36 |
+
|
| 37 |
+
```python
|
| 38 |
+
from PIL import Image
|
| 39 |
+
import requests
|
| 40 |
+
|
| 41 |
+
from transformers import CLIPProcessor, CLIPModel
|
| 42 |
+
|
| 43 |
+
model = CLIPModel.from_pretrained("openai/clip-vit-large-patch14")
|
| 44 |
+
processor = CLIPProcessor.from_pretrained("openai/clip-vit-large-patch14")
|
| 45 |
+
|
| 46 |
+
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
|
| 47 |
+
image = Image.open(requests.get(url, stream=True).raw)
|
| 48 |
+
|
| 49 |
+
inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)
|
| 50 |
+
|
| 51 |
+
outputs = model(**inputs)
|
| 52 |
+
logits_per_image = outputs.logits_per_image # this is the image-text similarity score
|
| 53 |
+
probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities
|
| 54 |
+
```
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
## Model Use
|
| 58 |
+
|
| 59 |
+
### Intended Use
|
| 60 |
+
|
| 61 |
+
The model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such models - the CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis.
|
| 62 |
+
|
| 63 |
+
#### Primary intended uses
|
| 64 |
+
|
| 65 |
+
The primary intended users of these models are AI researchers.
|
| 66 |
+
|
| 67 |
+
We primarily imagine the model will be used by researchers to better understand robustness, generalization, and other capabilities, biases, and constraints of computer vision models.
|
| 68 |
+
|
| 69 |
+
### Out-of-Scope Use Cases
|
| 70 |
+
|
| 71 |
+
**Any** deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful.
|
| 72 |
+
|
| 73 |
+
Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use.
|
| 74 |
+
|
| 75 |
+
Since the model has not been purposefully trained in or evaluated on any languages other than English, its use should be limited to English language use cases.
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
## Data
|
| 80 |
+
|
| 81 |
+
The model was trained on publicly available image-caption data. This was done through a combination of crawling a handful of websites and using commonly-used pre-existing image datasets such as [YFCC100M](http://projects.dfki.uni-kl.de/yfcc100m/). A large portion of the data comes from our crawling of the internet. This means that the data is more representative of people and societies most connected to the internet which tend to skew towards more developed nations, and younger, male users.
|
| 82 |
+
|
| 83 |
+
### Data Mission Statement
|
| 84 |
+
|
| 85 |
+
Our goal with building this dataset was to test out robustness and generalizability in computer vision tasks. As a result, the focus was on gathering large quantities of data from different publicly-available internet data sources. The data was gathered in a mostly non-interventionist manner. However, we only crawled websites that had policies against excessively violent and adult images and allowed us to filter out such content. We do not intend for this dataset to be used as the basis for any commercial or deployed model and will not be releasing the dataset.
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
## Performance and Limitations
|
| 90 |
+
|
| 91 |
+
### Performance
|
| 92 |
+
|
| 93 |
+
We have evaluated the performance of CLIP on a wide range of benchmarks across a variety of computer vision datasets such as OCR to texture recognition to fine-grained classification. The paper describes model performance on the following datasets:
|
| 94 |
+
|
| 95 |
+
- Food101
|
| 96 |
+
- CIFAR10
|
| 97 |
+
- CIFAR100
|
| 98 |
+
- Birdsnap
|
| 99 |
+
- SUN397
|
| 100 |
+
- Stanford Cars
|
| 101 |
+
- FGVC Aircraft
|
| 102 |
+
- VOC2007
|
| 103 |
+
- DTD
|
| 104 |
+
- Oxford-IIIT Pet dataset
|
| 105 |
+
- Caltech101
|
| 106 |
+
- Flowers102
|
| 107 |
+
- MNIST
|
| 108 |
+
- SVHN
|
| 109 |
+
- IIIT5K
|
| 110 |
+
- Hateful Memes
|
| 111 |
+
- SST-2
|
| 112 |
+
- UCF101
|
| 113 |
+
- Kinetics700
|
| 114 |
+
- Country211
|
| 115 |
+
- CLEVR Counting
|
| 116 |
+
- KITTI Distance
|
| 117 |
+
- STL-10
|
| 118 |
+
- RareAct
|
| 119 |
+
- Flickr30
|
| 120 |
+
- MSCOCO
|
| 121 |
+
- ImageNet
|
| 122 |
+
- ImageNet-A
|
| 123 |
+
- ImageNet-R
|
| 124 |
+
- ImageNet Sketch
|
| 125 |
+
- ObjectNet (ImageNet Overlap)
|
| 126 |
+
- Youtube-BB
|
| 127 |
+
- ImageNet-Vid
|
| 128 |
+
|
| 129 |
+
## Limitations
|
| 130 |
+
|
| 131 |
+
CLIP and our analysis of it have a number of limitations. CLIP currently struggles with respect to certain tasks such as fine grained classification and counting objects. CLIP also poses issues with regards to fairness and bias which we discuss in the paper and briefly in the next section. Additionally, our approach to testing CLIP also has an important limitation- in many cases we have used linear probes to evaluate the performance of CLIP and there is evidence suggesting that linear probes can underestimate model performance.
|
| 132 |
+
|
| 133 |
+
### Bias and Fairness
|
| 134 |
+
|
| 135 |
+
We find that the performance of CLIP - and the specific biases it exhibits - can depend significantly on class design and the choices one makes for categories to include and exclude. We tested the risk of certain kinds of denigration with CLIP by classifying images of people from [Fairface](https://arxiv.org/abs/1908.04913) into crime-related and non-human animal categories. We found significant disparities with respect to race and gender. Additionally, we found that these disparities could shift based on how the classes were constructed. (Details captured in the Broader Impacts Section in the paper).
|
| 136 |
+
|
| 137 |
+
We also tested the performance of CLIP on gender, race and age classification using the Fairface dataset (We default to using race categories as they are constructed in the Fairface dataset.) in order to assess quality of performance across different demographics. We found accuracy >96% across all races for gender classification with ‘Middle Eastern’ having the highest accuracy (98.4%) and ‘White’ having the lowest (96.5%). Additionally, CLIP averaged ~93% for racial classification and ~63% for age classification. Our use of evaluations to test for gender, race and age classification as well as denigration harms is simply to evaluate performance of the model across people and surface potential risks and not to demonstrate an endorsement/enthusiasm for such tasks.
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
## Feedback
|
| 142 |
+
|
| 143 |
+
### Where to send questions or comments about the model
|
| 144 |
+
|
| 145 |
+
Please use [this Google Form](https://forms.gle/Uv7afRH5dvY34ZEs9)
|
text_encoder_2/config.json
ADDED
|
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "clip-vit-large-patch14/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPModel"
|
| 5 |
+
],
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "clip",
|
| 9 |
+
"projection_dim": 768,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": null,
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"bad_words_ids": null,
|
| 16 |
+
"bos_token_id": 0,
|
| 17 |
+
"chunk_size_feed_forward": 0,
|
| 18 |
+
"cross_attention_hidden_size": null,
|
| 19 |
+
"decoder_start_token_id": null,
|
| 20 |
+
"diversity_penalty": 0.0,
|
| 21 |
+
"do_sample": false,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
+
"early_stopping": false,
|
| 24 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 25 |
+
"eos_token_id": 2,
|
| 26 |
+
"finetuning_task": null,
|
| 27 |
+
"forced_bos_token_id": null,
|
| 28 |
+
"forced_eos_token_id": null,
|
| 29 |
+
"hidden_act": "quick_gelu",
|
| 30 |
+
"hidden_size": 768,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "LABEL_0",
|
| 33 |
+
"1": "LABEL_1"
|
| 34 |
+
},
|
| 35 |
+
"initializer_factor": 1.0,
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"intermediate_size": 3072,
|
| 38 |
+
"is_decoder": false,
|
| 39 |
+
"is_encoder_decoder": false,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1
|
| 43 |
+
},
|
| 44 |
+
"layer_norm_eps": 1e-05,
|
| 45 |
+
"length_penalty": 1.0,
|
| 46 |
+
"max_length": 20,
|
| 47 |
+
"max_position_embeddings": 77,
|
| 48 |
+
"min_length": 0,
|
| 49 |
+
"model_type": "clip_text_model",
|
| 50 |
+
"no_repeat_ngram_size": 0,
|
| 51 |
+
"num_attention_heads": 12,
|
| 52 |
+
"num_beam_groups": 1,
|
| 53 |
+
"num_beams": 1,
|
| 54 |
+
"num_hidden_layers": 12,
|
| 55 |
+
"num_return_sequences": 1,
|
| 56 |
+
"output_attentions": false,
|
| 57 |
+
"output_hidden_states": false,
|
| 58 |
+
"output_scores": false,
|
| 59 |
+
"pad_token_id": 1,
|
| 60 |
+
"prefix": null,
|
| 61 |
+
"problem_type": null,
|
| 62 |
+
"projection_dim" : 768,
|
| 63 |
+
"pruned_heads": {},
|
| 64 |
+
"remove_invalid_values": false,
|
| 65 |
+
"repetition_penalty": 1.0,
|
| 66 |
+
"return_dict": true,
|
| 67 |
+
"return_dict_in_generate": false,
|
| 68 |
+
"sep_token_id": null,
|
| 69 |
+
"task_specific_params": null,
|
| 70 |
+
"temperature": 1.0,
|
| 71 |
+
"tie_encoder_decoder": false,
|
| 72 |
+
"tie_word_embeddings": true,
|
| 73 |
+
"tokenizer_class": null,
|
| 74 |
+
"top_k": 50,
|
| 75 |
+
"top_p": 1.0,
|
| 76 |
+
"torch_dtype": null,
|
| 77 |
+
"torchscript": false,
|
| 78 |
+
"transformers_version": "4.16.0.dev0",
|
| 79 |
+
"use_bfloat16": false,
|
| 80 |
+
"vocab_size": 49408
|
| 81 |
+
},
|
| 82 |
+
"text_config_dict": {
|
| 83 |
+
"hidden_size": 768,
|
| 84 |
+
"intermediate_size": 3072,
|
| 85 |
+
"num_attention_heads": 12,
|
| 86 |
+
"num_hidden_layers": 12,
|
| 87 |
+
"projection_dim": 768
|
| 88 |
+
},
|
| 89 |
+
"torch_dtype": "float32",
|
| 90 |
+
"transformers_version": null,
|
| 91 |
+
"vision_config": {
|
| 92 |
+
"_name_or_path": "",
|
| 93 |
+
"add_cross_attention": false,
|
| 94 |
+
"architectures": null,
|
| 95 |
+
"attention_dropout": 0.0,
|
| 96 |
+
"bad_words_ids": null,
|
| 97 |
+
"bos_token_id": null,
|
| 98 |
+
"chunk_size_feed_forward": 0,
|
| 99 |
+
"cross_attention_hidden_size": null,
|
| 100 |
+
"decoder_start_token_id": null,
|
| 101 |
+
"diversity_penalty": 0.0,
|
| 102 |
+
"do_sample": false,
|
| 103 |
+
"dropout": 0.0,
|
| 104 |
+
"early_stopping": false,
|
| 105 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 106 |
+
"eos_token_id": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 1024,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 4096,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 16,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_hidden_layers": 24,
|
| 136 |
+
"num_return_sequences": 1,
|
| 137 |
+
"output_attentions": false,
|
| 138 |
+
"output_hidden_states": false,
|
| 139 |
+
"output_scores": false,
|
| 140 |
+
"pad_token_id": null,
|
| 141 |
+
"patch_size": 14,
|
| 142 |
+
"prefix": null,
|
| 143 |
+
"problem_type": null,
|
| 144 |
+
"projection_dim" : 768,
|
| 145 |
+
"pruned_heads": {},
|
| 146 |
+
"remove_invalid_values": false,
|
| 147 |
+
"repetition_penalty": 1.0,
|
| 148 |
+
"return_dict": true,
|
| 149 |
+
"return_dict_in_generate": false,
|
| 150 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tie_encoder_decoder": false,
|
| 154 |
+
"tie_word_embeddings": true,
|
| 155 |
+
"tokenizer_class": null,
|
| 156 |
+
"top_k": 50,
|
| 157 |
+
"top_p": 1.0,
|
| 158 |
+
"torch_dtype": null,
|
| 159 |
+
"torchscript": false,
|
| 160 |
+
"transformers_version": "4.16.0.dev0",
|
| 161 |
+
"use_bfloat16": false
|
| 162 |
+
},
|
| 163 |
+
"vision_config_dict": {
|
| 164 |
+
"hidden_size": 1024,
|
| 165 |
+
"intermediate_size": 4096,
|
| 166 |
+
"num_attention_heads": 16,
|
| 167 |
+
"num_hidden_layers": 24,
|
| 168 |
+
"patch_size": 14,
|
| 169 |
+
"projection_dim": 768
|
| 170 |
+
}
|
| 171 |
+
}
|
text_encoder_2/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:156f677ed4495acd1ec7197249c091b85c240267c82f2f7f2e4eae4177931fed
|
| 3 |
+
size 1710486359
|
text_encoder_2/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2bf730a0c7debf160f7a6b50b3aaf3703e7e88ac73de7a314903141db026dcb
|
| 3 |
+
size 1710540580
|
text_encoder_2/preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": 224,
|
| 3 |
+
"do_center_crop": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
| 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 |
+
"resample": 3,
|
| 18 |
+
"size": 224
|
| 19 |
+
}
|
text_encoder_2/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1a17cdbe0f36fec524f5cafb1c261ea3bbbc13e346e0f74fc9eb0460dedd0d3
|
| 3 |
+
size 1710671599
|
text_encoder_2/tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f154e925c18270d662d28f6261523c2ff6e80f1f05292cb034db41d5951c7a4
|
| 3 |
+
size 1711114176
|
tokenizer/.ipynb_checkpoints/tokenizer-checkpoint.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 12845056,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 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 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2_5_VLProcessor"
|
| 19 |
+
}
|
tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"additional_special_tokens": [
|
| 182 |
+
"<|im_start|>",
|
| 183 |
+
"<|im_end|>",
|
| 184 |
+
"<|object_ref_start|>",
|
| 185 |
+
"<|object_ref_end|>",
|
| 186 |
+
"<|box_start|>",
|
| 187 |
+
"<|box_end|>",
|
| 188 |
+
"<|quad_start|>",
|
| 189 |
+
"<|quad_end|>",
|
| 190 |
+
"<|vision_start|>",
|
| 191 |
+
"<|vision_end|>",
|
| 192 |
+
"<|vision_pad|>",
|
| 193 |
+
"<|image_pad|>",
|
| 194 |
+
"<|video_pad|>"
|
| 195 |
+
],
|
| 196 |
+
"bos_token": null,
|
| 197 |
+
"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 %}",
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"model_max_length": 131072,
|
| 202 |
+
"pad_token": "<|endoftext|>",
|
| 203 |
+
"split_special_tokens": false,
|
| 204 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 205 |
+
"unk_token": null,
|
| 206 |
+
"add_bos_token": false
|
| 207 |
+
}
|
tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_2/.ipynb_checkpoints/merges-checkpoint.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_2/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_2/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
|
tokenizer_2/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_2/tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"single_word": false,
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"__type": "AddedToken"
|
| 9 |
+
},
|
| 10 |
+
"bos_token": {
|
| 11 |
+
"content": "<|startoftext|>",
|
| 12 |
+
"single_word": false,
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"__type": "AddedToken"
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|endoftext|>",
|
| 20 |
+
"single_word": false,
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"__type": "AddedToken"
|
| 25 |
+
},
|
| 26 |
+
"pad_token": "<|endoftext|>",
|
| 27 |
+
"add_prefix_space": false,
|
| 28 |
+
"errors": "replace",
|
| 29 |
+
"do_lower_case": true,
|
| 30 |
+
"name_or_path": "openai/clip-vit-base-patch32",
|
| 31 |
+
"model_max_length": 77,
|
| 32 |
+
"special_tokens_map_file": "./special_tokens_map.json",
|
| 33 |
+
"tokenizer_class": "CLIPTokenizer"
|
| 34 |
+
}
|
tokenizer_2/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer/.ipynb_checkpoints/config-checkpoint.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "Kandinsky5Transformer3DModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"in_visual_dim": 16,
|
| 5 |
+
"out_visual_dim": 16,
|
| 6 |
+
"time_dim": 512,
|
| 7 |
+
"patch_size": [
|
| 8 |
+
1,
|
| 9 |
+
2,
|
| 10 |
+
2
|
| 11 |
+
],
|
| 12 |
+
"model_dim": 1792,
|
| 13 |
+
"ff_dim": 7168,
|
| 14 |
+
"num_text_blocks": 2,
|
| 15 |
+
"num_visual_blocks": 32,
|
| 16 |
+
"axes_dims": [
|
| 17 |
+
16,
|
| 18 |
+
24,
|
| 19 |
+
24
|
| 20 |
+
],
|
| 21 |
+
"visual_cond": true,
|
| 22 |
+
"in_text_dim": 3584,
|
| 23 |
+
"in_text_dim2": 768,
|
| 24 |
+
"attention_type": "nabla",
|
| 25 |
+
"attention_causal": false,
|
| 26 |
+
"attention_local": false,
|
| 27 |
+
"attention_glob": false,
|
| 28 |
+
"attention_window": 3,
|
| 29 |
+
"attention_P": 0.9,
|
| 30 |
+
"attention_wT": 11,
|
| 31 |
+
"attention_wW": 3,
|
| 32 |
+
"attention_wH": 3,
|
| 33 |
+
"attention_add_sta": true,
|
| 34 |
+
"attention_method": "topcdf"
|
| 35 |
+
}
|
| 36 |
+
|
| 37 |
+
|
transformer/config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "Kandinsky5Transformer3DModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"in_visual_dim": 16,
|
| 5 |
+
"out_visual_dim": 16,
|
| 6 |
+
"time_dim": 512,
|
| 7 |
+
"patch_size": [
|
| 8 |
+
1,
|
| 9 |
+
2,
|
| 10 |
+
2
|
| 11 |
+
],
|
| 12 |
+
"model_dim": 1792,
|
| 13 |
+
"ff_dim": 7168,
|
| 14 |
+
"num_text_blocks": 2,
|
| 15 |
+
"num_visual_blocks": 32,
|
| 16 |
+
"axes_dims": [
|
| 17 |
+
16,
|
| 18 |
+
24,
|
| 19 |
+
24
|
| 20 |
+
],
|
| 21 |
+
"visual_cond": true,
|
| 22 |
+
"in_text_dim": 3584,
|
| 23 |
+
"in_text_dim2": 768,
|
| 24 |
+
"attention_type": "nabla",
|
| 25 |
+
"attention_causal": false,
|
| 26 |
+
"attention_local": false,
|
| 27 |
+
"attention_glob": false,
|
| 28 |
+
"attention_window": 3,
|
| 29 |
+
"attention_P": 0.9,
|
| 30 |
+
"attention_wT": 11,
|
| 31 |
+
"attention_wW": 3,
|
| 32 |
+
"attention_wH": 3,
|
| 33 |
+
"attention_add_sta": true,
|
| 34 |
+
"attention_method": "topcdf"
|
| 35 |
+
}
|
| 36 |
+
|
| 37 |
+
|
transformer/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da64436073b6e4ccb23ed41aa8f83c86f261f4bcff714bd20fb6c49b3110f4a8
|
| 3 |
+
size 4573130528
|
vae/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKLHunyuanVideo",
|
| 3 |
+
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"block_out_channels": [
|
| 6 |
+
128,
|
| 7 |
+
256,
|
| 8 |
+
512,
|
| 9 |
+
512
|
| 10 |
+
],
|
| 11 |
+
"down_block_types": [
|
| 12 |
+
"HunyuanVideoDownBlock3D",
|
| 13 |
+
"HunyuanVideoDownBlock3D",
|
| 14 |
+
"HunyuanVideoDownBlock3D",
|
| 15 |
+
"HunyuanVideoDownBlock3D"
|
| 16 |
+
],
|
| 17 |
+
"in_channels": 3,
|
| 18 |
+
"latent_channels": 16,
|
| 19 |
+
"layers_per_block": 2,
|
| 20 |
+
"mid_block_add_attention": true,
|
| 21 |
+
"norm_num_groups": 32,
|
| 22 |
+
"out_channels": 3,
|
| 23 |
+
"scaling_factor": 0.476986,
|
| 24 |
+
"spatial_compression_ratio": 8,
|
| 25 |
+
"temporal_compression_ratio": 4,
|
| 26 |
+
"up_block_types": [
|
| 27 |
+
"HunyuanVideoUpBlock3D",
|
| 28 |
+
"HunyuanVideoUpBlock3D",
|
| 29 |
+
"HunyuanVideoUpBlock3D",
|
| 30 |
+
"HunyuanVideoUpBlock3D"
|
| 31 |
+
]
|
| 32 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c68a6295f9034a88225fbafb1f3258291a08d57a1fdb938233fa57b1b8f4883
|
| 3 |
+
size 985943868
|