Upload folder using huggingface_hub
This commit is contained in:
parent
f58577e288
commit
c03ef5ea2c
35
.gitattributes
vendored
35
.gitattributes
vendored
@ -1,47 +1,40 @@
|
|||||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
*.model filter=lfs diff=lfs merge=lfs -text
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
|
||||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.tar 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
|
||||||
|
model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|||||||
47
README.md
47
README.md
@ -1,47 +0,0 @@
|
|||||||
---
|
|
||||||
license: Apache License 2.0
|
|
||||||
|
|
||||||
#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/Qwen2.5-VL-7B-Instruct')
|
|
||||||
```
|
|
||||||
Git下载
|
|
||||||
```
|
|
||||||
#Git模型下载
|
|
||||||
git clone https://www.modelscope.cn/Qwen/Qwen2.5-VL-7B-Instruct.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>
|
|
||||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@ -0,0 +1,3 @@
|
|||||||
|
{
|
||||||
|
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
||||||
|
}
|
||||||
61
config.json
Normal file
61
config.json
Normal file
@ -0,0 +1,61 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2_5_VLForConditionalGeneration"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"vision_start_token_id": 151652,
|
||||||
|
"vision_end_token_id": 151653,
|
||||||
|
"vision_token_id": 151654,
|
||||||
|
"image_token_id": 151655,
|
||||||
|
"video_token_id": 151656,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 3584,
|
||||||
|
"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_theta": 1000000.0,
|
||||||
|
"sliding_window": 32768,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.41.2",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vision_config": {
|
||||||
|
"depth": 32,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1280,
|
||||||
|
"intermediate_size": 3420,
|
||||||
|
"num_heads": 16,
|
||||||
|
"in_chans": 3,
|
||||||
|
"out_hidden_size": 3584,
|
||||||
|
"patch_size": 14,
|
||||||
|
"spatial_merge_size": 2,
|
||||||
|
"spatial_patch_size": 14,
|
||||||
|
"window_size": 112,
|
||||||
|
"fullatt_block_indexes": [
|
||||||
|
7,
|
||||||
|
15,
|
||||||
|
23,
|
||||||
|
31
|
||||||
|
],
|
||||||
|
"tokens_per_second": 2,
|
||||||
|
"temporal_patch_size": 2
|
||||||
|
},
|
||||||
|
"rope_scaling": {
|
||||||
|
"type": "mrope",
|
||||||
|
"mrope_section": [
|
||||||
|
16,
|
||||||
|
24,
|
||||||
|
24
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"vocab_size": 152064
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "vision-understanding", "allow_remote": true}
|
||||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"repetition_penalty": 1.05,
|
||||||
|
"temperature": 0.1,
|
||||||
|
"top_p": 0.001,
|
||||||
|
"top_k": 1,
|
||||||
|
"transformers_version": "4.37.0"
|
||||||
|
}
|
||||||
151387
merges.txt
Normal file
151387
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
BIN
model-00001-of-00005.safetensors
(Stored with Git LFS)
Normal file
BIN
model-00001-of-00005.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
BIN
model-00002-of-00005.safetensors
(Stored with Git LFS)
Normal file
BIN
model-00002-of-00005.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
BIN
model-00003-of-00005.safetensors
(Stored with Git LFS)
Normal file
BIN
model-00003-of-00005.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
BIN
model-00004-of-00005.safetensors
(Stored with Git LFS)
Normal file
BIN
model-00004-of-00005.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
BIN
model-00005-of-00005.safetensors
(Stored with Git LFS)
Normal file
BIN
model-00005-of-00005.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
736
model.safetensors.index.json
Normal file
736
model.safetensors.index.json
Normal file
@ -0,0 +1,736 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 16584333312
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.0.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.1.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.10.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.11.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.12.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.13.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.14.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.15.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.16.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.17.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.18.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.19.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.2.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.20.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.21.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.22.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.23.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.24.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.25.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.26.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.27.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.28.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.29.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.3.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.30.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.31.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.4.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.5.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.6.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.7.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.8.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.attn.proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.attn.proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.norm1.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.blocks.9.norm2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.merger.ln_q.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.merger.mlp.0.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.merger.mlp.0.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.merger.mlp.2.bias": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.merger.mlp.2.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"visual.patch_embed.proj.weight": "model-00001-of-00005.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
19
preprocessor_config.json
Normal file
19
preprocessor_config.json
Normal file
@ -0,0 +1,19 @@
|
|||||||
|
{
|
||||||
|
"min_pixels": 3136,
|
||||||
|
"max_pixels": 12845056,
|
||||||
|
"patch_size": 14,
|
||||||
|
"temporal_patch_size": 2,
|
||||||
|
"merge_size": 2,
|
||||||
|
"image_mean": [
|
||||||
|
0.48145466,
|
||||||
|
0.4578275,
|
||||||
|
0.40821073
|
||||||
|
],
|
||||||
|
"image_std": [
|
||||||
|
0.26862954,
|
||||||
|
0.26130258,
|
||||||
|
0.27577711
|
||||||
|
],
|
||||||
|
"image_processor_type": "Qwen2_5_VLImageProcessor",
|
||||||
|
"processor_class": "Qwen2_5_VLProcessor"
|
||||||
|
}
|
||||||
303282
tokenizer.json
Normal file
303282
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@ -0,0 +1,207 @@
|
|||||||
|
{
|
||||||
|
"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,
|
||||||
|
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null,
|
||||||
|
"add_bos_token": false
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Loading…
Reference in New Issue
Block a user