mirror of
https://www.modelscope.cn/ZhipuAI/GLM-4.1V-9B-Thinking.git
synced 2026-04-02 11:02:56 +08:00
init
This commit is contained in:
root
51
README.md
51
README.md
@ -1,51 +0,0 @@
|
||||
---
|
||||
frameworks:
|
||||
- Pytorch
|
||||
license: MIT License
|
||||
tasks:
|
||||
- image-captioning
|
||||
|
||||
#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('ZhipuAI/GLM-4.1V-9B-Thinking')
|
||||
```
|
||||
Git下载
|
||||
```
|
||||
#Git模型下载
|
||||
git clone https://www.modelscope.cn/ZhipuAI/GLM-4.1V-9B-Thinking.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>
|
||||
33
chat_template.jinja
Normal file
33
chat_template.jinja
Normal file
@ -0,0 +1,33 @@
|
||||
[gMASK]<sop>
|
||||
{%- for msg in messages %}
|
||||
{%- if msg.role == 'system' %}
|
||||
<|system|>
|
||||
{{ msg.content }}
|
||||
{%- elif msg.role == 'user' %}
|
||||
<|user|>{{ '\n' }}
|
||||
|
||||
{%- if msg.content is string %}
|
||||
{{ msg.content }}
|
||||
{%- else %}
|
||||
{%- for item in msg.content %}
|
||||
{%- if item.type == 'video' or 'video' in item %}
|
||||
<|begin_of_video|><|video|><|end_of_video|>
|
||||
{%- elif item.type == 'image' or 'image' in item %}
|
||||
<|begin_of_image|><|image|><|end_of_image|>
|
||||
{%- elif item.type == 'text' %}
|
||||
{{ item.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{%- elif msg.role == 'assistant' %}
|
||||
{%- if msg.metadata %}
|
||||
<|assistant|>{{ msg.metadata }}
|
||||
{{ msg.content }}
|
||||
{%- else %}
|
||||
<|assistant|>
|
||||
{{ msg.content }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{% if add_generation_prompt %}<|assistant|>
|
||||
{% endif %}
|
||||
61
config.json
Normal file
61
config.json
Normal file
@ -0,0 +1,61 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Glm4vForConditionalGeneration"
|
||||
],
|
||||
"model_type": "glm4v",
|
||||
"attention_bias": true,
|
||||
"attention_dropout": 0.0,
|
||||
"pad_token_id": 151329,
|
||||
"eos_token_id": [
|
||||
151329,
|
||||
151336,
|
||||
151338,
|
||||
151348
|
||||
],
|
||||
"image_start_token_id": 151339,
|
||||
"image_end_token_id": 151340,
|
||||
"video_start_token_id": 151341,
|
||||
"video_end_token_id": 151342,
|
||||
"image_token_id": 151343,
|
||||
"video_token_id": 151344,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13696,
|
||||
"max_position_embeddings": 32768,
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.53.0dev",
|
||||
"use_cache": true,
|
||||
"vocab_size": 151552,
|
||||
"partial_rotary_factor": 0.5,
|
||||
"vision_config": {
|
||||
"hidden_size": 1536,
|
||||
"depth": 24,
|
||||
"num_heads": 12,
|
||||
"attention_bias": false,
|
||||
"intermediate_size": 13696,
|
||||
"hidden_act": "silu",
|
||||
"hidden_dropout_prob": 0.0,
|
||||
"initializer_range": 0.02,
|
||||
"image_size": 336,
|
||||
"patch_size": 14,
|
||||
"out_hidden_size": 4096,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"spatial_merge_size": 2,
|
||||
"temporal_patch_size": 2
|
||||
},
|
||||
"rope_scaling": {
|
||||
"type": "default",
|
||||
"mrope_section": [
|
||||
8,
|
||||
12,
|
||||
12
|
||||
]
|
||||
}
|
||||
}
|
||||
@ -1 +0,0 @@
|
||||
{"framework":"Pytorch","task":"image-captioning"}
|
||||
BIN
model-00001-of-00004.safetensors
(Stored with Git LFS)
Normal file
BIN
model-00001-of-00004.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
BIN
model-00002-of-00004.safetensors
(Stored with Git LFS)
Normal file
BIN
model-00002-of-00004.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
BIN
model-00003-of-00004.safetensors
(Stored with Git LFS)
Normal file
BIN
model-00003-of-00004.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
BIN
model-00004-of-00004.safetensors
(Stored with Git LFS)
Normal file
BIN
model-00004-of-00004.safetensors
(Stored with Git LFS)
Normal file
Binary file not shown.
711
model.safetensors.index.json
Normal file
711
model.safetensors.index.json
Normal file
@ -0,0 +1,711 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 20585554944
|
||||
},
|
||||
"weight_map": {
|
||||
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.post_self_attn_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.post_mlp_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.post_self_attn_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.post_mlp_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.post_self_attn_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.post_mlp_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.mlp.gate_up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.language_model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.post_self_attn_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.post_mlp_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.mlp.gate_up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.4.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.5.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.10.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.11.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.12.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.13.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.14.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.15.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.16.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.17.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.18.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.19.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.20.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.21.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.22.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.blocks.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.embed_tokens.weight": "model-00004-of-00004.safetensors",
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.downsample.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.downsample.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.post_projection_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.merger.post_projection_norm.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.visual.post_conv_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.visual.post_layernorm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
11
preprocessor_config.json
Normal file
11
preprocessor_config.json
Normal file
@ -0,0 +1,11 @@
|
||||
{
|
||||
"size": {"shortest_edge": 12544, "longest_edge": 9633792},
|
||||
"do_rescale": true,
|
||||
"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": "Glm4vImageProcessor",
|
||||
"processor_class": "Glm4vProcessor"
|
||||
}
|
||||
1423865
tokenizer.json
Normal file
1423865
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
225
tokenizer_config.json
Normal file
225
tokenizer_config.json
Normal file
@ -0,0 +1,225 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"151329": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151330": {
|
||||
"content": "[MASK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151331": {
|
||||
"content": "[gMASK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151332": {
|
||||
"content": "[sMASK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151333": {
|
||||
"content": "<sop>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151334": {
|
||||
"content": "<eop>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151335": {
|
||||
"content": "<|system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151336": {
|
||||
"content": "<|user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151337": {
|
||||
"content": "<|assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151338": {
|
||||
"content": "<|observation|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151339": {
|
||||
"content": "<|begin_of_image|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151340": {
|
||||
"content": "<|end_of_image|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151341": {
|
||||
"content": "<|begin_of_video|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151342": {
|
||||
"content": "<|end_of_video|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151343": {
|
||||
"content": "<|image|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151344": {
|
||||
"content": "<|video|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151345": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151346": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151347": {
|
||||
"content": "<answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151348": {
|
||||
"content": "</answer>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151349": {
|
||||
"content": "<|begin_of_box|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151350": {
|
||||
"content": "<|end_of_box|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151351": {
|
||||
"content": "<|sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"[MASK]",
|
||||
"[gMASK]",
|
||||
"[sMASK]",
|
||||
"<sop>",
|
||||
"<eop>",
|
||||
"<|system|>",
|
||||
"<|user|>",
|
||||
"<|assistant|>",
|
||||
"<|observation|>",
|
||||
"<|begin_of_image|>",
|
||||
"<|end_of_image|>",
|
||||
"<|begin_of_video|>",
|
||||
"<|end_of_video|>",
|
||||
"<|begin_of_box|>",
|
||||
"<|end_of_box|>",
|
||||
"<|sep|>",
|
||||
"<|image|>",
|
||||
"<|video|>",
|
||||
"<think>",
|
||||
"</think>",
|
||||
"<answer>",
|
||||
"</answer>"
|
||||
],
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"do_lower_case": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"pad_token": "<|endoftext|>",
|
||||
"model_input_names": [
|
||||
"input_ids",
|
||||
"attention_mask"
|
||||
],
|
||||
"model_max_length": 64000,
|
||||
"padding_side": "left",
|
||||
"remove_space": false,
|
||||
"tokenizer_class": "PreTrainedTokenizer"
|
||||
}
|
||||
11
video_preprocessor_config.json
Normal file
11
video_preprocessor_config.json
Normal file
@ -0,0 +1,11 @@
|
||||
{
|
||||
"size": {"shortest_edge": 12544, "longest_edge": 47040000},
|
||||
"do_rescale": true,
|
||||
"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],
|
||||
"video_processor_type": "Glm4vVideoProcessor",
|
||||
"processor_class": "Glm4vProcessor"
|
||||
}
|
||||
Reference in New Issue
Block a user