AI-ModelScope/Qwen2.5-VL-3B-sft-reasoning_and_grounding_changecoord_cpt636
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: AI-ModelScope/Qwen2.5-VL-3B-sft-reasoning_and_grounding_changecoord_cpt636
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-03 21:43:12 +08:00
commit e1e426ab78
25 changed files with 1837 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
.gitattributes vendored Normal file
View File

@@ -0,0 +1,68 @@
*.7z 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
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz 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
*.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
*tfevents* filter=lfs diff=lfs merge=lfs -text
merges.txt filter=lfs diff=lfs merge=lfs -text
model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
rng_state_1.pth filter=lfs diff=lfs merge=lfs -text
rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
rng_state_2.pth filter=lfs diff=lfs merge=lfs -text
rng_state_3.pth filter=lfs diff=lfs merge=lfs -text
rng_state_4.pth filter=lfs diff=lfs merge=lfs -text
rng_state_5.pth filter=lfs diff=lfs merge=lfs -text
rng_state_7.pth filter=lfs diff=lfs merge=lfs -text
rng_state_6.pth filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
vocab.json filter=lfs diff=lfs merge=lfs -text

48
README.md Normal file
View File

@@ -0,0 +1,48 @@
---
license: other
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('AI-ModelScope/Qwen2.5-VL-3B-sft-reasoning_and_grounding_changecoord_cpt636')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/AI-ModelScope/Qwen2.5-VL-3B-sft-reasoning_and_grounding_changecoord_cpt636.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>

24
added_tokens.json Normal file
View File

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

3
chat_template.json Normal file
View 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 %}"
}

65
config.json Normal file
View File

@@ -0,0 +1,65 @@
{
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"image_token_id": 151655,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 128000,
"max_window_layers": 70,
"model_type": "qwen2_5_vl",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"mrope_section": [
16,
24,
24
],
"rope_type": "default",
"type": "default"
},
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.0",
"use_cache": false,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"depth": 32,
"fullatt_block_indexes": [
7,
15,
23,
31
],
"hidden_act": "silu",
"hidden_size": 1280,
"in_channels": 3,
"in_chans": 3,
"intermediate_size": 3420,
"model_type": "qwen2_5_vl",
"num_heads": 16,
"out_hidden_size": 2048,
"patch_size": 14,
"spatial_merge_size": 2,
"spatial_patch_size": 14,
"temporal_patch_size": 2,
"tokens_per_second": 2,
"torch_dtype": "bfloat16",
"window_size": 112
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 151936
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "others", "allow_remote": true}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"attn_implementation": "flash_attention_2",
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 1e-06,
"transformers_version": "4.51.0"
}

BIN
merges.txt (Stored with Git LFS) Normal file
View File

Binary file not shown.

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c8110132b7c59603f21fee765ee9e07e4a8635bc4d715c79f3818719100f281e
size 4997750760

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8c6e0de4a5eed288aac75c984140eaf8396814ee574abf90aefa9b1095b404de
size 2511587184

831
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,831 @@
{
"metadata": {
"total_size": 7509245952
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
"model.norm.weight": "model-00002-of-00002.safetensors",
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
"visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
}
}

29
preprocessor_config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.48145466,
0.4578275,
0.40821073
],
"image_processor_type": "Qwen2VLImageProcessor",
"image_std": [
0.26862954,
0.26130258,
0.27577711
],
"max_pixels": 5720064,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 12845056,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}

3
rng_state_0.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:427efdeedfee5b17e33a7c2cdd4caf0696654b00256345a0ddc7fac50658351f
size 16325

3
rng_state_1.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ff881f936a1d6c245325b20940e3f1e454ea17800df0ebc3d07e5af8a35c316
size 16325

3
rng_state_2.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eb82aa8b5109fa7449b9bacff33e2ca7c9e83c900af10de5a9ead0df0babe57a
size 16325

3
rng_state_3.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ed75d53950e2c784799079aacd40ffa56badcbe253470bc19fcc1d1e0b6a2b2
size 16325

3
rng_state_4.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c1addf5fdc88e72d3f0aa8288bacb6c9d69ef916642567a2fef95a793cbeb86e
size 16325

3
rng_state_5.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f86f74d661dea63650ab7bc0a7f6b9895bef65498977d939963b6468efba3b4
size 16325

3
rng_state_6.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97063170624a256a95d11400ff19815a52d6b6e1e007c66d154517ff1b426a73
size 16325

3
rng_state_7.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:52e1ff53070f674ff85002c5e3dc4ce1abfc6f4014fa48362ae1da7fafd7ebdc
size 16325

31
special_tokens_map.json Normal file
View File

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

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
size 11421896

210
tokenizer_config.json Normal file
View File

@@ -0,0 +1,210 @@
{
"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,
"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 %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 24576,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"processor_class": "Qwen2_5_VLProcessor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

475
trainer_state.json Normal file
View File

@@ -0,0 +1,475 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9992144540455616,
"eval_steps": 500,
"global_step": 636,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.031421838177533384,
"grad_norm": 0.7421875,
"learning_rate": 9.999750543489357e-06,
"loss": 1.3149,
"step": 10
},
{
"epoch": 0.06284367635506677,
"grad_norm": 0.453125,
"learning_rate": 9.991022178937775e-06,
"loss": 0.9124,
"step": 20
},
{
"epoch": 0.09426551453260015,
"grad_norm": 0.99609375,
"learning_rate": 9.96984586911221e-06,
"loss": 0.8294,
"step": 30
},
{
"epoch": 0.12568735271013354,
"grad_norm": 0.294921875,
"learning_rate": 9.936274429154798e-06,
"loss": 0.8129,
"step": 40
},
{
"epoch": 0.15710919088766692,
"grad_norm": 0.33984375,
"learning_rate": 9.890391588496586e-06,
"loss": 0.7844,
"step": 50
},
{
"epoch": 0.1885310290652003,
"grad_norm": 0.283203125,
"learning_rate": 9.832311782030674e-06,
"loss": 0.7959,
"step": 60
},
{
"epoch": 0.2199528672427337,
"grad_norm": 0.306640625,
"learning_rate": 9.762179864703908e-06,
"loss": 0.7767,
"step": 70
},
{
"epoch": 0.2513747054202671,
"grad_norm": 0.3828125,
"learning_rate": 9.680170750238873e-06,
"loss": 0.7704,
"step": 80
},
{
"epoch": 0.2827965435978005,
"grad_norm": 0.3984375,
"learning_rate": 9.586488974887312e-06,
"loss": 0.7644,
"step": 90
},
{
"epoch": 0.31421838177533384,
"grad_norm": 0.3359375,
"learning_rate": 9.48136818730293e-06,
"loss": 0.7523,
"step": 100
},
{
"epoch": 0.34564021995286726,
"grad_norm": 0.31640625,
"learning_rate": 9.365070565805941e-06,
"loss": 0.7683,
"step": 110
},
{
"epoch": 0.3770620581304006,
"grad_norm": 0.2578125,
"learning_rate": 9.23788616449268e-06,
"loss": 0.7561,
"step": 120
},
{
"epoch": 0.408483896307934,
"grad_norm": 0.36328125,
"learning_rate": 9.100132189821156e-06,
"loss": 0.7601,
"step": 130
},
{
"epoch": 0.4399057344854674,
"grad_norm": 0.376953125,
"learning_rate": 8.952152209476812e-06,
"loss": 0.7559,
"step": 140
},
{
"epoch": 0.4713275726630008,
"grad_norm": 0.279296875,
"learning_rate": 8.794315295491571e-06,
"loss": 0.734,
"step": 150
},
{
"epoch": 0.5027494108405341,
"grad_norm": 0.349609375,
"learning_rate": 8.62701510375336e-06,
"loss": 0.7567,
"step": 160
},
{
"epoch": 0.5341712490180676,
"grad_norm": 0.1904296875,
"learning_rate": 8.450668892201819e-06,
"loss": 0.7396,
"step": 170
},
{
"epoch": 0.565593087195601,
"grad_norm": 0.2490234375,
"learning_rate": 8.265716480158914e-06,
"loss": 0.7424,
"step": 180
},
{
"epoch": 0.5970149253731343,
"grad_norm": 0.25390625,
"learning_rate": 8.072619151389951e-06,
"loss": 0.7442,
"step": 190
},
{
"epoch": 0.6284367635506677,
"grad_norm": 0.423828125,
"learning_rate": 7.8718585036308e-06,
"loss": 0.7211,
"step": 200
},
{
"epoch": 0.6598586017282011,
"grad_norm": 0.2041015625,
"learning_rate": 7.663935247450733e-06,
"loss": 0.743,
"step": 210
},
{
"epoch": 0.6912804399057345,
"grad_norm": 0.322265625,
"learning_rate": 7.449367957446566e-06,
"loss": 0.7389,
"step": 220
},
{
"epoch": 0.7227022780832679,
"grad_norm": 0.81640625,
"learning_rate": 7.2286917788826926e-06,
"loss": 0.7329,
"step": 230
},
{
"epoch": 0.7541241162608012,
"grad_norm": 0.416015625,
"learning_rate": 7.002457093002785e-06,
"loss": 0.7447,
"step": 240
},
{
"epoch": 0.7855459544383346,
"grad_norm": 0.474609375,
"learning_rate": 6.77122814434192e-06,
"loss": 0.7209,
"step": 250
},
{
"epoch": 0.816967792615868,
"grad_norm": 0.28125,
"learning_rate": 6.535581633462728e-06,
"loss": 0.7413,
"step": 260
},
{
"epoch": 0.8483896307934015,
"grad_norm": 0.3828125,
"learning_rate": 6.296105278625368e-06,
"loss": 0.7308,
"step": 270
},
{
"epoch": 0.8798114689709348,
"grad_norm": 0.302734375,
"learning_rate": 6.053396349978632e-06,
"loss": 0.7302,
"step": 280
},
{
"epoch": 0.9112333071484682,
"grad_norm": 0.7109375,
"learning_rate": 5.808060179927983e-06,
"loss": 0.7383,
"step": 290
},
{
"epoch": 0.9426551453260016,
"grad_norm": 0.4140625,
"learning_rate": 5.560708653395796e-06,
"loss": 0.7183,
"step": 300
},
{
"epoch": 0.974076983503535,
"grad_norm": 0.318359375,
"learning_rate": 5.3119586817391655e-06,
"loss": 0.7379,
"step": 310
},
{
"epoch": 1.0062843676355067,
"grad_norm": 0.236328125,
"learning_rate": 5.062430664131463e-06,
"loss": 0.7395,
"step": 320
},
{
"epoch": 1.03770620581304,
"grad_norm": 0.31640625,
"learning_rate": 4.812746940245032e-06,
"loss": 0.7115,
"step": 330
},
{
"epoch": 1.0691280439905735,
"grad_norm": 1.0625,
"learning_rate": 4.563530238094161e-06,
"loss": 0.7328,
"step": 340
},
{
"epoch": 1.1005498821681068,
"grad_norm": 0.4921875,
"learning_rate": 4.315402120909486e-06,
"loss": 0.7178,
"step": 350
},
{
"epoch": 1.1319717203456403,
"grad_norm": 0.287109375,
"learning_rate": 4.068981436917471e-06,
"loss": 0.7277,
"step": 360
},
{
"epoch": 1.1633935585231736,
"grad_norm": 0.2373046875,
"learning_rate": 3.8248827758912535e-06,
"loss": 0.7299,
"step": 370
},
{
"epoch": 1.194815396700707,
"grad_norm": 0.35546875,
"learning_rate": 3.5837149363224045e-06,
"loss": 0.7189,
"step": 380
},
{
"epoch": 1.2262372348782404,
"grad_norm": 0.296875,
"learning_rate": 3.3460794070364923e-06,
"loss": 0.7371,
"step": 390
},
{
"epoch": 1.2576590730557737,
"grad_norm": 0.2734375,
"learning_rate": 3.1125688670394682e-06,
"loss": 0.7148,
"step": 400
},
{
"epoch": 1.2890809112333073,
"grad_norm": 0.365234375,
"learning_rate": 2.8837657073363344e-06,
"loss": 0.7275,
"step": 410
},
{
"epoch": 1.3205027494108406,
"grad_norm": 0.5859375,
"learning_rate": 2.660240578408776e-06,
"loss": 0.7234,
"step": 420
},
{
"epoch": 1.3519245875883739,
"grad_norm": 0.498046875,
"learning_rate": 2.442550966974444e-06,
"loss": 0.7171,
"step": 430
},
{
"epoch": 1.3833464257659074,
"grad_norm": 0.26171875,
"learning_rate": 2.2312398055775496e-06,
"loss": 0.7332,
"step": 440
},
{
"epoch": 1.4147682639434407,
"grad_norm": 0.220703125,
"learning_rate": 2.0268341184785674e-06,
"loss": 0.7167,
"step": 450
},
{
"epoch": 1.446190102120974,
"grad_norm": 0.380859375,
"learning_rate": 1.829843707220243e-06,
"loss": 0.7235,
"step": 460
},
{
"epoch": 1.4776119402985075,
"grad_norm": 0.2255859375,
"learning_rate": 1.6407598791482294e-06,
"loss": 0.7253,
"step": 470
},
{
"epoch": 1.5090337784760408,
"grad_norm": 0.359375,
"learning_rate": 1.4600542220575038e-06,
"loss": 0.7132,
"step": 480
},
{
"epoch": 1.5404556166535741,
"grad_norm": 0.3828125,
"learning_rate": 1.2881774280206554e-06,
"loss": 0.7309,
"step": 490
},
{
"epoch": 1.5718774548311076,
"grad_norm": 0.4375,
"learning_rate": 1.125558169331521e-06,
"loss": 0.7232,
"step": 500
},
{
"epoch": 1.6032992930086412,
"grad_norm": 0.2734375,
"learning_rate": 9.726020293676308e-07,
"loss": 0.7284,
"step": 510
},
{
"epoch": 1.6347211311861742,
"grad_norm": 0.330078125,
"learning_rate": 8.296904910379622e-07,
"loss": 0.7282,
"step": 520
},
{
"epoch": 1.6661429693637078,
"grad_norm": 1.5078125,
"learning_rate": 6.971799853388867e-07,
"loss": 0.7159,
"step": 530
},
{
"epoch": 1.6975648075412413,
"grad_norm": 1.1171875,
"learning_rate": 5.754010023912693e-07,
"loss": 0.7349,
"step": 540
},
{
"epoch": 1.7289866457187746,
"grad_norm": 0.328125,
"learning_rate": 4.646572671758687e-07,
"loss": 0.7208,
"step": 550
},
{
"epoch": 1.7604084838963079,
"grad_norm": 0.361328125,
"learning_rate": 3.6522498202278434e-07,
"loss": 0.7253,
"step": 560
},
{
"epoch": 1.7918303220738414,
"grad_norm": 0.283203125,
"learning_rate": 2.773521377442523e-07,
"loss": 0.7246,
"step": 570
},
{
"epoch": 1.8232521602513747,
"grad_norm": 0.484375,
"learning_rate": 2.012578951288724e-07,
"loss": 0.7161,
"step": 580
},
{
"epoch": 1.854673998428908,
"grad_norm": 0.298828125,
"learning_rate": 1.3713203833984446e-07,
"loss": 0.7316,
"step": 590
},
{
"epoch": 1.8860958366064415,
"grad_norm": 0.234375,
"learning_rate": 8.513450158049109e-08,
"loss": 0.7133,
"step": 600
},
{
"epoch": 1.9175176747839748,
"grad_norm": 0.2353515625,
"learning_rate": 4.5394970207591206e-08,
"loss": 0.7306,
"step": 610
},
{
"epoch": 1.9489395129615081,
"grad_norm": 1.0390625,
"learning_rate": 1.8012557287367394e-08,
"loss": 0.722,
"step": 620
},
{
"epoch": 1.9803613511390417,
"grad_norm": 0.408203125,
"learning_rate": 3.0555564008305504e-09,
"loss": 0.717,
"step": 630
}
],
"logging_steps": 10,
"max_steps": 636,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500.0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.042156006349629e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

BIN
vocab.json (Stored with Git LFS) Normal file
View File

Binary file not shown.