mirror of
https://www.modelscope.cn/Qwen/Qwen-Image-2512.git
synced 2026-04-02 20:02:54 +08:00
Upload folder using ModelScope SDK (batch 1/1)
This commit is contained in:
Cherrytest
17
.gitattributes
vendored
17
.gitattributes
vendored
@ -45,3 +45,20 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|||||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
transformer/diffusion_pytorch_model-00002-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
transformer/diffusion_pytorch_model-00007-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
transformer/diffusion_pytorch_model-00001-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
transformer/diffusion_pytorch_model-00006-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
transformer/diffusion_pytorch_model-00008-of-00009.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-00004-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer/vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
text_encoder/model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
transformer/diffusion_pytorch_model-00003-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
vae/diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer/merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
transformer/diffusion_pytorch_model-00005-of-00009.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
|
||||||
|
transformer/diffusion_pytorch_model-00009-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
47
README.md
47
README.md
@ -1,48 +1,3 @@
|
|||||||
---
|
---
|
||||||
license: Apache License 2.0
|
license: apache-2.0
|
||||||
tags: []
|
|
||||||
|
|
||||||
#model-type:
|
|
||||||
##如 gpt、phi、llama、chatglm、baichuan 等
|
|
||||||
#- gpt
|
|
||||||
|
|
||||||
#domain:
|
|
||||||
##如 nlp、cv、audio、multi-modal
|
|
||||||
#- nlp
|
|
||||||
|
|
||||||
#language:
|
|
||||||
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
|
|
||||||
#- cn
|
|
||||||
|
|
||||||
#metrics:
|
|
||||||
##如 CIDEr、Blue、ROUGE 等
|
|
||||||
#- CIDEr
|
|
||||||
|
|
||||||
#tags:
|
|
||||||
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
|
|
||||||
#- pretrained
|
|
||||||
|
|
||||||
#tools:
|
|
||||||
##如 vllm、fastchat、llamacpp、AdaSeq 等
|
|
||||||
#- vllm
|
|
||||||
---
|
---
|
||||||
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
|
|
||||||
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
|
||||||
|
|
||||||
SDK下载
|
|
||||||
```bash
|
|
||||||
#安装ModelScope
|
|
||||||
pip install modelscope
|
|
||||||
```
|
|
||||||
```python
|
|
||||||
#SDK模型下载
|
|
||||||
from modelscope import snapshot_download
|
|
||||||
model_dir = snapshot_download('Qwen/Qwen-Image-2512')
|
|
||||||
```
|
|
||||||
Git下载
|
|
||||||
```
|
|
||||||
#Git模型下载
|
|
||||||
git clone https://www.modelscope.cn/Qwen/Qwen-Image-2512.git
|
|
||||||
```
|
|
||||||
|
|
||||||
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-to-image", "allow_remote": true}
|
||||||
24
model_index.json
Normal file
24
model_index.json
Normal file
@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"_class_name": "QwenImagePipeline",
|
||||||
|
"_diffusers_version": "0.36.0.dev0",
|
||||||
|
"scheduler": [
|
||||||
|
"diffusers",
|
||||||
|
"FlowMatchEulerDiscreteScheduler"
|
||||||
|
],
|
||||||
|
"text_encoder": [
|
||||||
|
"transformers",
|
||||||
|
"Qwen2_5_VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"tokenizer": [
|
||||||
|
"transformers",
|
||||||
|
"Qwen2Tokenizer"
|
||||||
|
],
|
||||||
|
"transformer": [
|
||||||
|
"diffusers",
|
||||||
|
"QwenImageTransformer2DModel"
|
||||||
|
],
|
||||||
|
"vae": [
|
||||||
|
"diffusers",
|
||||||
|
"AutoencoderKLQwenImage"
|
||||||
|
]
|
||||||
|
}
|
||||||
18
scheduler/scheduler_config.json
Normal file
18
scheduler/scheduler_config.json
Normal 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
|
||||||
|
}
|
||||||
132
text_encoder/config.json
Normal file
132
text_encoder/config.json
Normal file
@ -0,0 +1,132 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2_5_VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"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": {
|
||||||
|
"_name_or_path": "/cpfs01/haoyangzhang/pretrained_weights/Qwen2.5-VL",
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2_5_VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"dtype": "float32",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 3584,
|
||||||
|
"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,
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"vocab_size": 152064
|
||||||
|
},
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.57.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"video_token_id": 151656,
|
||||||
|
"vision_config": {
|
||||||
|
"depth": 32,
|
||||||
|
"dtype": "float32",
|
||||||
|
"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,
|
||||||
|
"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
14
text_encoder/generation_config.json
Normal 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": "4.57.1"
|
||||||
|
}
|
||||||
3
text_encoder/model-00001-of-00004.safetensors
Normal file
3
text_encoder/model-00001-of-00004.safetensors
Normal 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
3
text_encoder/model-00002-of-00004.safetensors
Normal 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
3
text_encoder/model-00003-of-00004.safetensors
Normal 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
3
text_encoder/model-00004-of-00004.safetensors
Normal 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
737
text_encoder/model.safetensors.index.json
Normal 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
24
tokenizer/added_tokens.json
Normal 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
54
tokenizer/chat_template.jinja
Normal 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
3
tokenizer/merges.txt
Normal 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
31
tokenizer/special_tokens_map.json
Normal 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
207
tokenizer/tokenizer_config.json
Normal 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
3
tokenizer/vocab.json
Normal file
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:87a257b04b17642a0688c98cd1df89c398bda4fee532d6f88b38a659ecb4ac8d
|
||||||
|
size 3383407
|
||||||
17
transformer/config.json
Normal file
17
transformer/config.json
Normal 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
|
||||||
|
}
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1abb592dfb6701994f11dbbe1228d99fef1246e2cdd119a73e030da7c2b4d795
|
||||||
|
size 4989364312
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f725018bd0b6b54a1529b38f20d38840b69aceefe843b443949e0e035799e88b
|
||||||
|
size 4984214160
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3de6b71c7d756b4ead46c475f02bc27ff9efe64c43ce2b6790afb9fea81d821b
|
||||||
|
size 4946470000
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c6877663a33e453e3e7fb73d1c6d006612a3e7b29d6a9f84d697383015e2f4b8
|
||||||
|
size 4984213736
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:31ce58f75ddfaa3851a95397ae5b22e8e435ded5f021dd7d903e138e12586d2e
|
||||||
|
size 4946471896
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e8c1521290054c832e50086e65e50222e8e9b85cefb595667bc82ee091854772
|
||||||
|
size 4946451560
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:33847ad316bdc789f4b0c522cd0c388a025c6254e6e5b3f9626a6afe175655d3
|
||||||
|
size 4908690520
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:770716dc6e0c7007c2e8fba297f075cae23b45985a4cda3ec4dae5f7b559c03c
|
||||||
|
size 4984232856
|
||||||
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3f8213dfaaf5aacba65f42c33bc77bb5926506755b1503fa6fa323750088fc0c
|
||||||
|
size 1170918840
|
||||||
1940
transformer/diffusion_pytorch_model.safetensors.index.json
Normal file
1940
transformer/diffusion_pytorch_model.safetensors.index.json
Normal file
File diff suppressed because it is too large
Load Diff
56
vae/config.json
Normal file
56
vae/config.json
Normal 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
3
vae/diffusion_pytorch_model.safetensors
Normal file
@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0c8bc8b758c649abef9ea407b95408389a3b2f610d0d10fcb054fe171d0a8344
|
||||||
|
size 253806966
|
||||||
Reference in New Issue
Block a user