ai-models/Qwen-Image-Edit-2509
2
0
Fork 0
mirror of https://www.modelscope.cn/Qwen/Qwen-Image-Edit-2509.git synced 2026-04-02 11:02:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

Upload to Qwen/Qwen-Image-Edit-2509 on ModelScope hub

Browse Source
This commit is contained in:
Cherrytest
2025-09-22 09:51:07 +00:00
parent 7f2a89196c
commit 34d77c44b4
34 changed files with 3672 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
.gitattributes vendored
View File

@ -45,3 +45,19 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
processor/merges.txt filter=lfs diff=lfs merge=lfs -text
transformer/diffusion_pytorch_model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
transformer/diffusion_pytorch_model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer/merges.txt filter=lfs diff=lfs merge=lfs -text
text_encoder/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
text_encoder/model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
transformer/diffusion_pytorch_model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
transformer/diffusion_pytorch_model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
processor/vocab.json filter=lfs diff=lfs merge=lfs -text
transformer/diffusion_pytorch_model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
tokenizer/vocab.json filter=lfs diff=lfs merge=lfs -text
vae/diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text
text_encoder/model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
text_encoder/model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text

28
model_index.json Normal file
View File

@ -0,0 +1,28 @@
{
"_class_name": "QwenImageEditPlusPipeline",
"_diffusers_version": "0.36.0.dev0",
"processor": [
"transformers",
"Qwen2VLProcessor"
],
"scheduler": [
"diffusers",
"FlowMatchEulerDiscreteScheduler"
],
"text_encoder": [
"transformers",
"Qwen2_5_VLForConditionalGeneration"
],
"tokenizer": [
"transformers",
"Qwen2Tokenizer"
],
"transformer": [
"diffusers",
"QwenImageTransformer2DModel"
],
"vae": [
"diffusers",
"AutoencoderKLQwenImage"
]
}

24
processor/added_tokens.json Normal file
View File

@ -0,0 +1,24 @@
{
"</tool_call>": 151658,
"<tool_call>": 151657,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

7
processor/chat_template.jinja Normal file
View File

@ -0,0 +1,7 @@
{% 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
You are a helpful assistant.<|im_end|>
{% endif %}<|im_start|>{{ message['role'] }}
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
{% 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|>
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
{% endif %}

3
processor/merges.txt Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
size 1671853

37
processor/preprocessor_config.json Normal file
View File

@ -0,0 +1,37 @@
{
"crop_size": null,
"data_format": "channels_first",
"default_to_square": true,
"device": null,
"disable_grouping": null,
"do_center_crop": null,
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessorFast",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"input_data_format": null,
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"return_tensors": null,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}

31
processor/special_tokens_map.json Normal file
View File

@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
processor/tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

208
processor/tokenizer_config.json Normal file
View File

@ -0,0 +1,208 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"processor_class": "Qwen2VLProcessor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

43
processor/video_preprocessor_config.json Normal file
View File

@ -0,0 +1,43 @@
{
"crop_size": null,
"data_format": "channels_first",
"default_to_square": true,
"device": null,
"do_center_crop": null,
"do_convert_rgb": true,
"do_normalize": true,
"do_pad": null,
"do_rescale": true,
"do_resize": true,
"do_sample_frames": false,
"fps": null,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"input_data_format": null,
"max_frames": 768,
"max_pixels": 12845056,
"merge_size": 2,
"min_frames": 4,
"min_pixels": 3136,
"num_frames": null,
"patch_size": 14,
"processor_class": "Qwen2VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"size_divisor": null,
"temporal_patch_size": 2,
"video_metadata": null,
"video_processor_type": "Qwen2VLVideoProcessor"
}

3
processor/vocab.json Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
size 2776833

18
scheduler/scheduler_config.json Normal file
View File

@ -0,0 +1,18 @@
{
"_class_name": "FlowMatchEulerDiscreteScheduler",
"_diffusers_version": "0.36.0.dev0",
"base_image_seq_len": 256,
"base_shift": 0.5,
"invert_sigmas": false,
"max_image_seq_len": 8192,
"max_shift": 0.9,
"num_train_timesteps": 1000,
"shift": 1.0,
"shift_terminal": 0.02,
"stochastic_sampling": false,
"time_shift_type": "exponential",
"use_beta_sigmas": false,
"use_dynamic_shifting": true,
"use_exponential_sigmas": false,
"use_karras_sigmas": false
}

135
text_encoder/config.json Normal file
View File

@ -0,0 +1,135 @@
{
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "qwen2_5_vl",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"text_config": {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_token_id": null,
"initializer_range": 0.02,
"intermediate_size": 18944,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 128000,
"max_window_layers": 28,
"model_type": "qwen2_5_vl_text",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": null,
"torch_dtype": "float32",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": null,
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
},
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.55.4",
"use_cache": true,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"depth": 32,
"fullatt_block_indexes": [
7,
15,
23,
31
],
"hidden_act": "silu",
"hidden_size": 1280,
"in_channels": 3,
"in_chans": 3,
"initializer_range": 0.02,
"intermediate_size": 3420,
"model_type": "qwen2_5_vl",
"num_heads": 16,
"out_hidden_size": 3584,
"patch_size": 14,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"temporal_patch_size": 2,
"tokens_per_second": 2,
"torch_dtype": "float32",
"window_size": 112
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 152064
}

14
text_encoder/generation_config.json Normal file
View File

@ -0,0 +1,14 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.1,
"top_k": 1,
"top_p": 0.001,
"transformers_version": "4.55.4"
}

3
text_encoder/model-00001-of-00004.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d725335e4ea2399be706469e4b8807716a8fa64bd03468252e9f7acf2415fee4
size 4968243304

3
text_encoder/model-00002-of-00004.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b1830db6908dcc76df3a71492acbcf2b8cac130114cf1f3c2d9edae8de8c6de3
size 4991495816

3
text_encoder/model-00003-of-00004.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:09c1807c6d00d7cab94f7db39d4c02ebb8537225ccde383861ac48db97945aa6
size 4932751040

3
text_encoder/model-00004-of-00004.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5dd068336d14d45ffb43cef374d286cc6ba9d8741b028f90a7d040d847961f4a
size 1691924384

737
text_encoder/model.safetensors.index.json Normal file
View File

@ -0,0 +1,737 @@
{
"metadata": {
"total_parameters": 8292166656,
"total_size": 16584333312
},
"weight_map": {
"lm_head.weight": "model-00004-of-00004.safetensors",
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors",
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
}
}

24
tokenizer/added_tokens.json Normal file
View File

@ -0,0 +1,24 @@
{
"</tool_call>": 151658,
"<tool_call>": 151657,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

54
tokenizer/chat_template.jinja Normal file
View File

@ -0,0 +1,54 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are a helpful assistant.' }}
{%- endif %}
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0]['role'] == 'system' %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- message.content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

3
tokenizer/merges.txt Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
size 1671853

31
tokenizer/special_tokens_map.json Normal file
View File

@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

207
tokenizer/tokenizer_config.json Normal file
View File

@ -0,0 +1,207 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

3
tokenizer/vocab.json Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:87a257b04b17642a0688c98cd1df89c398bda4fee532d6f88b38a659ecb4ac8d
size 3383407

17
transformer/config.json Normal file
View File

@ -0,0 +1,17 @@
{
"_class_name": "QwenImageTransformer2DModel",
"_diffusers_version": "0.36.0.dev0",
"attention_head_dim": 128,
"axes_dims_rope": [
16,
56,
56
],
"guidance_embeds": false,
"in_channels": 64,
"joint_attention_dim": 3584,
"num_attention_heads": 24,
"num_layers": 60,
"out_channels": 16,
"patch_size": 2
}

3
transformer/diffusion_pytorch_model-00001-of-00005.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:784a8efc4dcea09ba20b534bbe9e5fae3367d929525031a4bd26c5ddb7eb18e5
size 9973578592

3
transformer/diffusion_pytorch_model-00002-of-00005.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:86ce21e5e3bdecfbeaa31aa587c03d0d1af6ab05d79c127149e8217f81e0247f
size 9987326072

3
transformer/diffusion_pytorch_model-00003-of-00005.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c6a046daa991f3b32c3ae39ff95e6e7220455265fcbbb643e9f556bea8641d02
size 9987307440

3
transformer/diffusion_pytorch_model-00004-of-00005.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c28bf871d5db0a6397843eca3987e58ba2c3013d287d5d4a1271d68e158ce7e8
size 9930685712

3
transformer/diffusion_pytorch_model-00005-of-00005.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd2844e5cafb03b16bed9556aa29c15396a787e17c38a0eda7f5a1281497c76a
size 982130472

1940
transformer/diffusion_pytorch_model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

56
vae/config.json Normal file
View File

@ -0,0 +1,56 @@
{
"_class_name": "AutoencoderKLQwenImage",
"_diffusers_version": "0.36.0.dev0",
"attn_scales": [],
"base_dim": 96,
"dim_mult": [
1,
2,
4,
4
],
"dropout": 0.0,
"latents_mean": [
-0.7571,
-0.7089,
-0.9113,
0.1075,
-0.1745,
0.9653,
-0.1517,
1.5508,
0.4134,
-0.0715,
0.5517,
-0.3632,
-0.1922,
-0.9497,
0.2503,
-0.2921
],
"latents_std": [
2.8184,
1.4541,
2.3275,
2.6558,
1.2196,
1.7708,
2.6052,
2.0743,
3.2687,
2.1526,
2.8652,
1.5579,
1.6382,
1.1253,
2.8251,
1.916
],
"num_res_blocks": 2,
"temperal_downsample": [
false,
true,
true
],
"z_dim": 16
}

3
vae/diffusion_pytorch_model.safetensors Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344
size 253806966