Upload folder using huggingface_hub
Browse files- README.md +31 -3
- chat_template.json +3 -0
- config.json +2 -5
- generation_config.json +13 -12
- model-00001-of-00004.safetensors +2 -2
- model-00002-of-00004.safetensors +2 -2
- model-00003-of-00004.safetensors +2 -2
- model-00004-of-00004.safetensors +2 -2
- model.safetensors.index.json +448 -449
README.md
CHANGED
|
@@ -5,7 +5,12 @@ base_model:
|
|
| 5 |
- Qwen/Qwen3-VL-8B-Instruct
|
| 6 |
license: apache-2.0
|
| 7 |
pipeline_tag: image-text-to-text
|
|
|
|
| 8 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
<div>
|
| 10 |
<p style="margin-top: 0;margin-bottom: 0;">
|
| 11 |
<em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
|
|
@@ -79,10 +84,10 @@ This is the weight repository for Qwen3-VL-8B-Instruct.
|
|
| 79 |
|
| 80 |
**Multimodal performance**
|
| 81 |
|
| 82 |
-
![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/
|
| 83 |
|
| 84 |
**Pure text performance**
|
| 85 |
-
![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/
|
| 86 |
|
| 87 |
## Quickstart
|
| 88 |
|
|
@@ -114,7 +119,7 @@ model = Qwen3VLForConditionalGeneration.from_pretrained(
|
|
| 114 |
# device_map="auto",
|
| 115 |
# )
|
| 116 |
|
| 117 |
-
processor = AutoProcessor.from_pretrained("Qwen/
|
| 118 |
|
| 119 |
messages = [
|
| 120 |
{
|
|
@@ -137,6 +142,7 @@ inputs = processor.apply_chat_template(
|
|
| 137 |
return_dict=True,
|
| 138 |
return_tensors="pt"
|
| 139 |
)
|
|
|
|
| 140 |
|
| 141 |
# Inference: Generation of the output
|
| 142 |
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
|
@@ -149,6 +155,28 @@ output_text = processor.batch_decode(
|
|
| 149 |
print(output_text)
|
| 150 |
```
|
| 151 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 152 |
|
| 153 |
|
| 154 |
## Citation
|
|
|
|
| 5 |
- Qwen/Qwen3-VL-8B-Instruct
|
| 6 |
license: apache-2.0
|
| 7 |
pipeline_tag: image-text-to-text
|
| 8 |
+
library_name: transformers
|
| 9 |
---
|
| 10 |
+
> [!NOTE]
|
| 11 |
+
> Includes Unsloth **chat template fixes**! <br> For `llama.cpp`, use `--jinja`
|
| 12 |
+
>
|
| 13 |
+
|
| 14 |
<div>
|
| 15 |
<p style="margin-top: 0;margin-bottom: 0;">
|
| 16 |
<em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
|
|
|
|
| 84 |
|
| 85 |
**Multimodal performance**
|
| 86 |
|
| 87 |
+
|
| 88 |
|
| 89 |
**Pure text performance**
|
| 90 |
+
|
| 91 |
|
| 92 |
## Quickstart
|
| 93 |
|
|
|
|
| 119 |
# device_map="auto",
|
| 120 |
# )
|
| 121 |
|
| 122 |
+
processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-8B-Instruct")
|
| 123 |
|
| 124 |
messages = [
|
| 125 |
{
|
|
|
|
| 142 |
return_dict=True,
|
| 143 |
return_tensors="pt"
|
| 144 |
)
|
| 145 |
+
inputs = inputs.to(model.device)
|
| 146 |
|
| 147 |
# Inference: Generation of the output
|
| 148 |
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
|
|
|
| 155 |
print(output_text)
|
| 156 |
```
|
| 157 |
|
| 158 |
+
### Generation Hyperparameters
|
| 159 |
+
#### VL
|
| 160 |
+
```bash
|
| 161 |
+
export greedy='false'
|
| 162 |
+
export top_p=0.8
|
| 163 |
+
export top_k=20
|
| 164 |
+
export temperature=0.7
|
| 165 |
+
export repetition_penalty=1.0
|
| 166 |
+
export presence_penalty=1.5
|
| 167 |
+
export out_seq_length=16384
|
| 168 |
+
```
|
| 169 |
+
|
| 170 |
+
#### Text
|
| 171 |
+
```bash
|
| 172 |
+
export greedy='false'
|
| 173 |
+
export top_p=1.0
|
| 174 |
+
export top_k=40
|
| 175 |
+
export repetition_penalty=1.0
|
| 176 |
+
export presence_penalty=2.0
|
| 177 |
+
export temperature=1.0
|
| 178 |
+
export out_seq_length=32768
|
| 179 |
+
```
|
| 180 |
|
| 181 |
|
| 182 |
## Citation
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
| 3 |
+
}
|
config.json
CHANGED
|
@@ -2,8 +2,6 @@
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3VLForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"torch_dtype": "bfloat16",
|
| 6 |
-
"eos_token_id": 151645,
|
| 7 |
"image_token_id": 151655,
|
| 8 |
"model_type": "qwen3_vl",
|
| 9 |
"pad_token_id": 151654,
|
|
@@ -38,7 +36,7 @@
|
|
| 38 |
"vocab_size": 151936
|
| 39 |
},
|
| 40 |
"tie_word_embeddings": false,
|
| 41 |
-
"transformers_version": "4.57.
|
| 42 |
"unsloth_fixed": true,
|
| 43 |
"video_token_id": 151656,
|
| 44 |
"vision_config": {
|
|
@@ -48,7 +46,6 @@
|
|
| 48 |
24
|
| 49 |
],
|
| 50 |
"depth": 27,
|
| 51 |
-
"torch_dtype": "bfloat16",
|
| 52 |
"hidden_act": "gelu_pytorch_tanh",
|
| 53 |
"hidden_size": 1152,
|
| 54 |
"in_channels": 3,
|
|
@@ -64,4 +61,4 @@
|
|
| 64 |
},
|
| 65 |
"vision_end_token_id": 151653,
|
| 66 |
"vision_start_token_id": 151652
|
| 67 |
-
}
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"Qwen3VLForConditionalGeneration"
|
| 4 |
],
|
|
|
|
|
|
|
| 5 |
"image_token_id": 151655,
|
| 6 |
"model_type": "qwen3_vl",
|
| 7 |
"pad_token_id": 151654,
|
|
|
|
| 36 |
"vocab_size": 151936
|
| 37 |
},
|
| 38 |
"tie_word_embeddings": false,
|
| 39 |
+
"transformers_version": "4.57.1",
|
| 40 |
"unsloth_fixed": true,
|
| 41 |
"video_token_id": 151656,
|
| 42 |
"vision_config": {
|
|
|
|
| 46 |
24
|
| 47 |
],
|
| 48 |
"depth": 27,
|
|
|
|
| 49 |
"hidden_act": "gelu_pytorch_tanh",
|
| 50 |
"hidden_size": 1152,
|
| 51 |
"in_channels": 3,
|
|
|
|
| 61 |
},
|
| 62 |
"vision_end_token_id": 151653,
|
| 63 |
"vision_start_token_id": 151652
|
| 64 |
+
}
|
generation_config.json
CHANGED
|
@@ -1,13 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
|
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.8,
|
| 11 |
+
"repetition_penalty": 1.0,
|
| 12 |
+
"temperature": 0.7,
|
| 13 |
+
"transformers_version": "4.56.0"
|
| 14 |
+
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5d0aef0eb170fc7453a296c43c0849a56f510555d3588e4fd662bb35490aefa
|
| 3 |
+
size 4902275944
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8be88fb5501e4d5719a6d4cc212e6a13480330e74f3e8c77daa1a68f199106b5
|
| 3 |
+
size 4915962496
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83de00eafe6e0d57ccd009dbcf71c9974d74df2f016c27afb7e95aafd16b2192
|
| 3 |
+
size 4999831048
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a88b98e9f96270973f567e6a2c103ede6ccdf915ca3075e21c755604d0377a5
|
| 3 |
+
size 2716270024
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_parameters": 8767123696,
|
| 4 |
"total_size": 17534247392
|
| 5 |
},
|
| 6 |
"weight_map": {
|
|
@@ -127,11 +126,11 @@
|
|
| 127 |
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
-
"model.language_model.layers.19.input_layernorm.weight": "model-
|
| 131 |
-
"model.language_model.layers.19.mlp.down_proj.weight": "model-
|
| 132 |
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
-
"model.language_model.layers.19.mlp.up_proj.weight": "model-
|
| 134 |
-
"model.language_model.layers.19.post_attention_layernorm.weight": "model-
|
| 135 |
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
|
@@ -149,39 +148,39 @@
|
|
| 149 |
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
-
"model.language_model.layers.20.input_layernorm.weight": "model-
|
| 153 |
-
"model.language_model.layers.20.mlp.down_proj.weight": "model-
|
| 154 |
-
"model.language_model.layers.20.mlp.gate_proj.weight": "model-
|
| 155 |
-
"model.language_model.layers.20.mlp.up_proj.weight": "model-
|
| 156 |
-
"model.language_model.layers.20.post_attention_layernorm.weight": "model-
|
| 157 |
-
"model.language_model.layers.20.self_attn.k_norm.weight": "model-
|
| 158 |
-
"model.language_model.layers.20.self_attn.k_proj.weight": "model-
|
| 159 |
-
"model.language_model.layers.20.self_attn.o_proj.weight": "model-
|
| 160 |
-
"model.language_model.layers.20.self_attn.q_norm.weight": "model-
|
| 161 |
-
"model.language_model.layers.20.self_attn.q_proj.weight": "model-
|
| 162 |
-
"model.language_model.layers.20.self_attn.v_proj.weight": "model-
|
| 163 |
-
"model.language_model.layers.21.input_layernorm.weight": "model-
|
| 164 |
-
"model.language_model.layers.21.mlp.down_proj.weight": "model-
|
| 165 |
-
"model.language_model.layers.21.mlp.gate_proj.weight": "model-
|
| 166 |
-
"model.language_model.layers.21.mlp.up_proj.weight": "model-
|
| 167 |
-
"model.language_model.layers.21.post_attention_layernorm.weight": "model-
|
| 168 |
-
"model.language_model.layers.21.self_attn.k_norm.weight": "model-
|
| 169 |
-
"model.language_model.layers.21.self_attn.k_proj.weight": "model-
|
| 170 |
-
"model.language_model.layers.21.self_attn.o_proj.weight": "model-
|
| 171 |
-
"model.language_model.layers.21.self_attn.q_norm.weight": "model-
|
| 172 |
-
"model.language_model.layers.21.self_attn.q_proj.weight": "model-
|
| 173 |
-
"model.language_model.layers.21.self_attn.v_proj.weight": "model-
|
| 174 |
-
"model.language_model.layers.22.input_layernorm.weight": "model-
|
| 175 |
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
-
"model.language_model.layers.22.post_attention_layernorm.weight": "model-
|
| 179 |
-
"model.language_model.layers.22.self_attn.k_norm.weight": "model-
|
| 180 |
-
"model.language_model.layers.22.self_attn.k_proj.weight": "model-
|
| 181 |
-
"model.language_model.layers.22.self_attn.o_proj.weight": "model-
|
| 182 |
-
"model.language_model.layers.22.self_attn.q_norm.weight": "model-
|
| 183 |
-
"model.language_model.layers.22.self_attn.q_proj.weight": "model-
|
| 184 |
-
"model.language_model.layers.22.self_attn.v_proj.weight": "model-
|
| 185 |
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
|
@@ -292,39 +291,39 @@
|
|
| 292 |
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
-
"model.language_model.layers.32.input_layernorm.weight": "model-
|
| 296 |
-
"model.language_model.layers.32.mlp.down_proj.weight": "model-
|
| 297 |
-
"model.language_model.layers.32.mlp.gate_proj.weight": "model-
|
| 298 |
-
"model.language_model.layers.32.mlp.up_proj.weight": "model-
|
| 299 |
-
"model.language_model.layers.32.post_attention_layernorm.weight": "model-
|
| 300 |
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
-
"model.language_model.layers.33.input_layernorm.weight": "model-
|
| 307 |
-
"model.language_model.layers.33.mlp.down_proj.weight": "model-
|
| 308 |
-
"model.language_model.layers.33.mlp.gate_proj.weight": "model-
|
| 309 |
-
"model.language_model.layers.33.mlp.up_proj.weight": "model-
|
| 310 |
-
"model.language_model.layers.33.post_attention_layernorm.weight": "model-
|
| 311 |
-
"model.language_model.layers.33.self_attn.k_norm.weight": "model-
|
| 312 |
-
"model.language_model.layers.33.self_attn.k_proj.weight": "model-
|
| 313 |
-
"model.language_model.layers.33.self_attn.o_proj.weight": "model-
|
| 314 |
-
"model.language_model.layers.33.self_attn.q_norm.weight": "model-
|
| 315 |
-
"model.language_model.layers.33.self_attn.q_proj.weight": "model-
|
| 316 |
-
"model.language_model.layers.33.self_attn.v_proj.weight": "model-
|
| 317 |
-
"model.language_model.layers.34.input_layernorm.weight": "model-
|
| 318 |
-
"model.language_model.layers.34.mlp.down_proj.weight": "model-
|
| 319 |
-
"model.language_model.layers.34.mlp.gate_proj.weight": "model-
|
| 320 |
-
"model.language_model.layers.34.mlp.up_proj.weight": "model-
|
| 321 |
-
"model.language_model.layers.34.post_attention_layernorm.weight": "model-
|
| 322 |
-
"model.language_model.layers.34.self_attn.k_norm.weight": "model-
|
| 323 |
-
"model.language_model.layers.34.self_attn.k_proj.weight": "model-
|
| 324 |
-
"model.language_model.layers.34.self_attn.o_proj.weight": "model-
|
| 325 |
-
"model.language_model.layers.34.self_attn.q_norm.weight": "model-
|
| 326 |
-
"model.language_model.layers.34.self_attn.q_proj.weight": "model-
|
| 327 |
-
"model.language_model.layers.34.self_attn.v_proj.weight": "model-
|
| 328 |
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
|
@@ -332,9 +331,9 @@
|
|
| 332 |
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 335 |
-
"model.language_model.layers.35.self_attn.o_proj.weight": "model-
|
| 336 |
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
-
"model.language_model.layers.35.self_attn.q_proj.weight": "model-
|
| 338 |
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
|
@@ -358,401 +357,401 @@
|
|
| 358 |
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
-
"model.language_model.layers.6.input_layernorm.weight": "model-
|
| 362 |
-
"model.language_model.layers.6.mlp.down_proj.weight": "model-
|
| 363 |
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
-
"model.language_model.layers.6.post_attention_layernorm.weight": "model-
|
| 366 |
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
-
"model.language_model.layers.7.input_layernorm.weight": "model-
|
| 373 |
-
"model.language_model.layers.7.mlp.down_proj.weight": "model-
|
| 374 |
-
"model.language_model.layers.7.mlp.gate_proj.weight": "model-
|
| 375 |
-
"model.language_model.layers.7.mlp.up_proj.weight": "model-
|
| 376 |
-
"model.language_model.layers.7.post_attention_layernorm.weight": "model-
|
| 377 |
-
"model.language_model.layers.7.self_attn.k_norm.weight": "model-
|
| 378 |
-
"model.language_model.layers.7.self_attn.k_proj.weight": "model-
|
| 379 |
-
"model.language_model.layers.7.self_attn.o_proj.weight": "model-
|
| 380 |
-
"model.language_model.layers.7.self_attn.q_norm.weight": "model-
|
| 381 |
-
"model.language_model.layers.7.self_attn.q_proj.weight": "model-
|
| 382 |
-
"model.language_model.layers.7.self_attn.v_proj.weight": "model-
|
| 383 |
-
"model.language_model.layers.8.input_layernorm.weight": "model-
|
| 384 |
-
"model.language_model.layers.8.mlp.down_proj.weight": "model-
|
| 385 |
-
"model.language_model.layers.8.mlp.gate_proj.weight": "model-
|
| 386 |
-
"model.language_model.layers.8.mlp.up_proj.weight": "model-
|
| 387 |
-
"model.language_model.layers.8.post_attention_layernorm.weight": "model-
|
| 388 |
-
"model.language_model.layers.8.self_attn.k_norm.weight": "model-
|
| 389 |
-
"model.language_model.layers.8.self_attn.k_proj.weight": "model-
|
| 390 |
-
"model.language_model.layers.8.self_attn.o_proj.weight": "model-
|
| 391 |
-
"model.language_model.layers.8.self_attn.q_norm.weight": "model-
|
| 392 |
-
"model.language_model.layers.8.self_attn.q_proj.weight": "model-
|
| 393 |
-
"model.language_model.layers.8.self_attn.v_proj.weight": "model-
|
| 394 |
-
"model.language_model.layers.9.input_layernorm.weight": "model-
|
| 395 |
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
-
"model.language_model.layers.9.mlp.gate_proj.weight": "model-
|
| 397 |
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
-
"model.language_model.layers.9.post_attention_layernorm.weight": "model-
|
| 399 |
-
"model.language_model.layers.9.self_attn.k_norm.weight": "model-
|
| 400 |
-
"model.language_model.layers.9.self_attn.k_proj.weight": "model-
|
| 401 |
-
"model.language_model.layers.9.self_attn.o_proj.weight": "model-
|
| 402 |
-
"model.language_model.layers.9.self_attn.q_norm.weight": "model-
|
| 403 |
-
"model.language_model.layers.9.self_attn.q_proj.weight": "model-
|
| 404 |
-
"model.language_model.layers.9.self_attn.v_proj.weight": "model-
|
| 405 |
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 406 |
-
"model.visual.blocks.0.attn.proj.bias": "model-
|
| 407 |
-
"model.visual.blocks.0.attn.proj.weight": "model-
|
| 408 |
-
"model.visual.blocks.0.attn.qkv.bias": "model-
|
| 409 |
-
"model.visual.blocks.0.attn.qkv.weight": "model-
|
| 410 |
-
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-
|
| 411 |
-
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-
|
| 412 |
-
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-
|
| 413 |
-
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-
|
| 414 |
-
"model.visual.blocks.0.norm1.bias": "model-
|
| 415 |
-
"model.visual.blocks.0.norm1.weight": "model-
|
| 416 |
-
"model.visual.blocks.0.norm2.bias": "model-
|
| 417 |
-
"model.visual.blocks.0.norm2.weight": "model-
|
| 418 |
-
"model.visual.blocks.1.attn.proj.bias": "model-
|
| 419 |
-
"model.visual.blocks.1.attn.proj.weight": "model-
|
| 420 |
-
"model.visual.blocks.1.attn.qkv.bias": "model-
|
| 421 |
-
"model.visual.blocks.1.attn.qkv.weight": "model-
|
| 422 |
-
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-
|
| 423 |
-
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-
|
| 424 |
-
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-
|
| 425 |
-
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-
|
| 426 |
-
"model.visual.blocks.1.norm1.bias": "model-
|
| 427 |
-
"model.visual.blocks.1.norm1.weight": "model-
|
| 428 |
-
"model.visual.blocks.1.norm2.bias": "model-
|
| 429 |
-
"model.visual.blocks.1.norm2.weight": "model-
|
| 430 |
-
"model.visual.blocks.10.attn.proj.bias": "model-
|
| 431 |
-
"model.visual.blocks.10.attn.proj.weight": "model-
|
| 432 |
-
"model.visual.blocks.10.attn.qkv.bias": "model-
|
| 433 |
-
"model.visual.blocks.10.attn.qkv.weight": "model-
|
| 434 |
-
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-
|
| 435 |
-
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-
|
| 436 |
-
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-
|
| 437 |
-
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-
|
| 438 |
-
"model.visual.blocks.10.norm1.bias": "model-
|
| 439 |
-
"model.visual.blocks.10.norm1.weight": "model-
|
| 440 |
-
"model.visual.blocks.10.norm2.bias": "model-
|
| 441 |
-
"model.visual.blocks.10.norm2.weight": "model-
|
| 442 |
-
"model.visual.blocks.11.attn.proj.bias": "model-
|
| 443 |
-
"model.visual.blocks.11.attn.proj.weight": "model-
|
| 444 |
-
"model.visual.blocks.11.attn.qkv.bias": "model-
|
| 445 |
-
"model.visual.blocks.11.attn.qkv.weight": "model-
|
| 446 |
-
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-
|
| 447 |
-
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-
|
| 448 |
-
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-
|
| 449 |
-
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-
|
| 450 |
-
"model.visual.blocks.11.norm1.bias": "model-
|
| 451 |
-
"model.visual.blocks.11.norm1.weight": "model-
|
| 452 |
-
"model.visual.blocks.11.norm2.bias": "model-
|
| 453 |
-
"model.visual.blocks.11.norm2.weight": "model-
|
| 454 |
-
"model.visual.blocks.12.attn.proj.bias": "model-
|
| 455 |
-
"model.visual.blocks.12.attn.proj.weight": "model-
|
| 456 |
-
"model.visual.blocks.12.attn.qkv.bias": "model-
|
| 457 |
-
"model.visual.blocks.12.attn.qkv.weight": "model-
|
| 458 |
-
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-
|
| 459 |
-
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-
|
| 460 |
-
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-
|
| 461 |
-
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-
|
| 462 |
-
"model.visual.blocks.12.norm1.bias": "model-
|
| 463 |
-
"model.visual.blocks.12.norm1.weight": "model-
|
| 464 |
-
"model.visual.blocks.12.norm2.bias": "model-
|
| 465 |
-
"model.visual.blocks.12.norm2.weight": "model-
|
| 466 |
-
"model.visual.blocks.13.attn.proj.bias": "model-
|
| 467 |
-
"model.visual.blocks.13.attn.proj.weight": "model-
|
| 468 |
-
"model.visual.blocks.13.attn.qkv.bias": "model-
|
| 469 |
-
"model.visual.blocks.13.attn.qkv.weight": "model-
|
| 470 |
-
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-
|
| 471 |
-
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-
|
| 472 |
-
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-
|
| 473 |
-
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-
|
| 474 |
-
"model.visual.blocks.13.norm1.bias": "model-
|
| 475 |
-
"model.visual.blocks.13.norm1.weight": "model-
|
| 476 |
-
"model.visual.blocks.13.norm2.bias": "model-
|
| 477 |
-
"model.visual.blocks.13.norm2.weight": "model-
|
| 478 |
-
"model.visual.blocks.14.attn.proj.bias": "model-
|
| 479 |
-
"model.visual.blocks.14.attn.proj.weight": "model-
|
| 480 |
-
"model.visual.blocks.14.attn.qkv.bias": "model-
|
| 481 |
-
"model.visual.blocks.14.attn.qkv.weight": "model-
|
| 482 |
-
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-
|
| 483 |
-
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-
|
| 484 |
-
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-
|
| 485 |
-
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-
|
| 486 |
-
"model.visual.blocks.14.norm1.bias": "model-
|
| 487 |
-
"model.visual.blocks.14.norm1.weight": "model-
|
| 488 |
-
"model.visual.blocks.14.norm2.bias": "model-
|
| 489 |
-
"model.visual.blocks.14.norm2.weight": "model-
|
| 490 |
-
"model.visual.blocks.15.attn.proj.bias": "model-
|
| 491 |
-
"model.visual.blocks.15.attn.proj.weight": "model-
|
| 492 |
-
"model.visual.blocks.15.attn.qkv.bias": "model-
|
| 493 |
-
"model.visual.blocks.15.attn.qkv.weight": "model-
|
| 494 |
-
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-
|
| 495 |
-
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-
|
| 496 |
-
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-
|
| 497 |
-
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-
|
| 498 |
-
"model.visual.blocks.15.norm1.bias": "model-
|
| 499 |
-
"model.visual.blocks.15.norm1.weight": "model-
|
| 500 |
-
"model.visual.blocks.15.norm2.bias": "model-
|
| 501 |
-
"model.visual.blocks.15.norm2.weight": "model-
|
| 502 |
-
"model.visual.blocks.16.attn.proj.bias": "model-
|
| 503 |
-
"model.visual.blocks.16.attn.proj.weight": "model-
|
| 504 |
-
"model.visual.blocks.16.attn.qkv.bias": "model-
|
| 505 |
-
"model.visual.blocks.16.attn.qkv.weight": "model-
|
| 506 |
-
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-
|
| 507 |
-
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-
|
| 508 |
-
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-
|
| 509 |
-
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-
|
| 510 |
-
"model.visual.blocks.16.norm1.bias": "model-
|
| 511 |
-
"model.visual.blocks.16.norm1.weight": "model-
|
| 512 |
-
"model.visual.blocks.16.norm2.bias": "model-
|
| 513 |
-
"model.visual.blocks.16.norm2.weight": "model-
|
| 514 |
-
"model.visual.blocks.17.attn.proj.bias": "model-
|
| 515 |
-
"model.visual.blocks.17.attn.proj.weight": "model-
|
| 516 |
-
"model.visual.blocks.17.attn.qkv.bias": "model-
|
| 517 |
-
"model.visual.blocks.17.attn.qkv.weight": "model-
|
| 518 |
-
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-
|
| 519 |
-
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-
|
| 520 |
-
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-
|
| 521 |
-
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-
|
| 522 |
-
"model.visual.blocks.17.norm1.bias": "model-
|
| 523 |
-
"model.visual.blocks.17.norm1.weight": "model-
|
| 524 |
-
"model.visual.blocks.17.norm2.bias": "model-
|
| 525 |
-
"model.visual.blocks.17.norm2.weight": "model-
|
| 526 |
-
"model.visual.blocks.18.attn.proj.bias": "model-
|
| 527 |
-
"model.visual.blocks.18.attn.proj.weight": "model-
|
| 528 |
-
"model.visual.blocks.18.attn.qkv.bias": "model-
|
| 529 |
-
"model.visual.blocks.18.attn.qkv.weight": "model-
|
| 530 |
-
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-
|
| 531 |
-
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-
|
| 532 |
-
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-
|
| 533 |
-
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-
|
| 534 |
-
"model.visual.blocks.18.norm1.bias": "model-
|
| 535 |
-
"model.visual.blocks.18.norm1.weight": "model-
|
| 536 |
-
"model.visual.blocks.18.norm2.bias": "model-
|
| 537 |
-
"model.visual.blocks.18.norm2.weight": "model-
|
| 538 |
-
"model.visual.blocks.19.attn.proj.bias": "model-
|
| 539 |
-
"model.visual.blocks.19.attn.proj.weight": "model-
|
| 540 |
-
"model.visual.blocks.19.attn.qkv.bias": "model-
|
| 541 |
-
"model.visual.blocks.19.attn.qkv.weight": "model-
|
| 542 |
-
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-
|
| 543 |
-
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-
|
| 544 |
-
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-
|
| 545 |
-
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-
|
| 546 |
-
"model.visual.blocks.19.norm1.bias": "model-
|
| 547 |
-
"model.visual.blocks.19.norm1.weight": "model-
|
| 548 |
-
"model.visual.blocks.19.norm2.bias": "model-
|
| 549 |
-
"model.visual.blocks.19.norm2.weight": "model-
|
| 550 |
-
"model.visual.blocks.2.attn.proj.bias": "model-
|
| 551 |
-
"model.visual.blocks.2.attn.proj.weight": "model-
|
| 552 |
-
"model.visual.blocks.2.attn.qkv.bias": "model-
|
| 553 |
-
"model.visual.blocks.2.attn.qkv.weight": "model-
|
| 554 |
-
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-
|
| 555 |
-
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-
|
| 556 |
-
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-
|
| 557 |
-
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-
|
| 558 |
-
"model.visual.blocks.2.norm1.bias": "model-
|
| 559 |
-
"model.visual.blocks.2.norm1.weight": "model-
|
| 560 |
-
"model.visual.blocks.2.norm2.bias": "model-
|
| 561 |
-
"model.visual.blocks.2.norm2.weight": "model-
|
| 562 |
-
"model.visual.blocks.20.attn.proj.bias": "model-
|
| 563 |
-
"model.visual.blocks.20.attn.proj.weight": "model-
|
| 564 |
-
"model.visual.blocks.20.attn.qkv.bias": "model-
|
| 565 |
-
"model.visual.blocks.20.attn.qkv.weight": "model-
|
| 566 |
-
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-
|
| 567 |
-
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-
|
| 568 |
-
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-
|
| 569 |
-
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-
|
| 570 |
-
"model.visual.blocks.20.norm1.bias": "model-
|
| 571 |
-
"model.visual.blocks.20.norm1.weight": "model-
|
| 572 |
-
"model.visual.blocks.20.norm2.bias": "model-
|
| 573 |
-
"model.visual.blocks.20.norm2.weight": "model-
|
| 574 |
-
"model.visual.blocks.21.attn.proj.bias": "model-
|
| 575 |
-
"model.visual.blocks.21.attn.proj.weight": "model-
|
| 576 |
-
"model.visual.blocks.21.attn.qkv.bias": "model-
|
| 577 |
-
"model.visual.blocks.21.attn.qkv.weight": "model-
|
| 578 |
-
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-
|
| 579 |
-
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-
|
| 580 |
-
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-
|
| 581 |
-
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-
|
| 582 |
-
"model.visual.blocks.21.norm1.bias": "model-
|
| 583 |
-
"model.visual.blocks.21.norm1.weight": "model-
|
| 584 |
-
"model.visual.blocks.21.norm2.bias": "model-
|
| 585 |
-
"model.visual.blocks.21.norm2.weight": "model-
|
| 586 |
-
"model.visual.blocks.22.attn.proj.bias": "model-
|
| 587 |
-
"model.visual.blocks.22.attn.proj.weight": "model-
|
| 588 |
-
"model.visual.blocks.22.attn.qkv.bias": "model-
|
| 589 |
-
"model.visual.blocks.22.attn.qkv.weight": "model-
|
| 590 |
-
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-
|
| 591 |
-
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-
|
| 592 |
-
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-
|
| 593 |
-
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-
|
| 594 |
-
"model.visual.blocks.22.norm1.bias": "model-
|
| 595 |
-
"model.visual.blocks.22.norm1.weight": "model-
|
| 596 |
-
"model.visual.blocks.22.norm2.bias": "model-
|
| 597 |
-
"model.visual.blocks.22.norm2.weight": "model-
|
| 598 |
-
"model.visual.blocks.23.attn.proj.bias": "model-
|
| 599 |
-
"model.visual.blocks.23.attn.proj.weight": "model-
|
| 600 |
-
"model.visual.blocks.23.attn.qkv.bias": "model-
|
| 601 |
-
"model.visual.blocks.23.attn.qkv.weight": "model-
|
| 602 |
-
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-
|
| 603 |
-
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-
|
| 604 |
-
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-
|
| 605 |
-
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-
|
| 606 |
-
"model.visual.blocks.23.norm1.bias": "model-
|
| 607 |
-
"model.visual.blocks.23.norm1.weight": "model-
|
| 608 |
-
"model.visual.blocks.23.norm2.bias": "model-
|
| 609 |
-
"model.visual.blocks.23.norm2.weight": "model-
|
| 610 |
-
"model.visual.blocks.24.attn.proj.bias": "model-
|
| 611 |
-
"model.visual.blocks.24.attn.proj.weight": "model-
|
| 612 |
-
"model.visual.blocks.24.attn.qkv.bias": "model-
|
| 613 |
-
"model.visual.blocks.24.attn.qkv.weight": "model-
|
| 614 |
-
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-
|
| 615 |
-
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-
|
| 616 |
-
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-
|
| 617 |
-
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-
|
| 618 |
-
"model.visual.blocks.24.norm1.bias": "model-
|
| 619 |
-
"model.visual.blocks.24.norm1.weight": "model-
|
| 620 |
-
"model.visual.blocks.24.norm2.bias": "model-
|
| 621 |
-
"model.visual.blocks.24.norm2.weight": "model-
|
| 622 |
-
"model.visual.blocks.25.attn.proj.bias": "model-
|
| 623 |
-
"model.visual.blocks.25.attn.proj.weight": "model-
|
| 624 |
-
"model.visual.blocks.25.attn.qkv.bias": "model-
|
| 625 |
-
"model.visual.blocks.25.attn.qkv.weight": "model-
|
| 626 |
-
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-
|
| 627 |
-
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-
|
| 628 |
-
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-
|
| 629 |
-
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-
|
| 630 |
-
"model.visual.blocks.25.norm1.bias": "model-
|
| 631 |
-
"model.visual.blocks.25.norm1.weight": "model-
|
| 632 |
-
"model.visual.blocks.25.norm2.bias": "model-
|
| 633 |
-
"model.visual.blocks.25.norm2.weight": "model-
|
| 634 |
-
"model.visual.blocks.26.attn.proj.bias": "model-
|
| 635 |
-
"model.visual.blocks.26.attn.proj.weight": "model-
|
| 636 |
-
"model.visual.blocks.26.attn.qkv.bias": "model-
|
| 637 |
-
"model.visual.blocks.26.attn.qkv.weight": "model-
|
| 638 |
-
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-
|
| 639 |
-
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-
|
| 640 |
-
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-
|
| 641 |
-
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-
|
| 642 |
-
"model.visual.blocks.26.norm1.bias": "model-
|
| 643 |
-
"model.visual.blocks.26.norm1.weight": "model-
|
| 644 |
-
"model.visual.blocks.26.norm2.bias": "model-
|
| 645 |
-
"model.visual.blocks.26.norm2.weight": "model-
|
| 646 |
-
"model.visual.blocks.3.attn.proj.bias": "model-
|
| 647 |
-
"model.visual.blocks.3.attn.proj.weight": "model-
|
| 648 |
-
"model.visual.blocks.3.attn.qkv.bias": "model-
|
| 649 |
-
"model.visual.blocks.3.attn.qkv.weight": "model-
|
| 650 |
-
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-
|
| 651 |
-
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-
|
| 652 |
-
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-
|
| 653 |
-
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-
|
| 654 |
-
"model.visual.blocks.3.norm1.bias": "model-
|
| 655 |
-
"model.visual.blocks.3.norm1.weight": "model-
|
| 656 |
-
"model.visual.blocks.3.norm2.bias": "model-
|
| 657 |
-
"model.visual.blocks.3.norm2.weight": "model-
|
| 658 |
-
"model.visual.blocks.4.attn.proj.bias": "model-
|
| 659 |
-
"model.visual.blocks.4.attn.proj.weight": "model-
|
| 660 |
-
"model.visual.blocks.4.attn.qkv.bias": "model-
|
| 661 |
-
"model.visual.blocks.4.attn.qkv.weight": "model-
|
| 662 |
-
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-
|
| 663 |
-
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-
|
| 664 |
-
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-
|
| 665 |
-
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-
|
| 666 |
-
"model.visual.blocks.4.norm1.bias": "model-
|
| 667 |
-
"model.visual.blocks.4.norm1.weight": "model-
|
| 668 |
-
"model.visual.blocks.4.norm2.bias": "model-
|
| 669 |
-
"model.visual.blocks.4.norm2.weight": "model-
|
| 670 |
-
"model.visual.blocks.5.attn.proj.bias": "model-
|
| 671 |
-
"model.visual.blocks.5.attn.proj.weight": "model-
|
| 672 |
-
"model.visual.blocks.5.attn.qkv.bias": "model-
|
| 673 |
-
"model.visual.blocks.5.attn.qkv.weight": "model-
|
| 674 |
-
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-
|
| 675 |
-
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-
|
| 676 |
-
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-
|
| 677 |
-
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-
|
| 678 |
-
"model.visual.blocks.5.norm1.bias": "model-
|
| 679 |
-
"model.visual.blocks.5.norm1.weight": "model-
|
| 680 |
-
"model.visual.blocks.5.norm2.bias": "model-
|
| 681 |
-
"model.visual.blocks.5.norm2.weight": "model-
|
| 682 |
-
"model.visual.blocks.6.attn.proj.bias": "model-
|
| 683 |
-
"model.visual.blocks.6.attn.proj.weight": "model-
|
| 684 |
-
"model.visual.blocks.6.attn.qkv.bias": "model-
|
| 685 |
-
"model.visual.blocks.6.attn.qkv.weight": "model-
|
| 686 |
-
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-
|
| 687 |
-
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-
|
| 688 |
-
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-
|
| 689 |
-
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-
|
| 690 |
-
"model.visual.blocks.6.norm1.bias": "model-
|
| 691 |
-
"model.visual.blocks.6.norm1.weight": "model-
|
| 692 |
-
"model.visual.blocks.6.norm2.bias": "model-
|
| 693 |
-
"model.visual.blocks.6.norm2.weight": "model-
|
| 694 |
-
"model.visual.blocks.7.attn.proj.bias": "model-
|
| 695 |
-
"model.visual.blocks.7.attn.proj.weight": "model-
|
| 696 |
-
"model.visual.blocks.7.attn.qkv.bias": "model-
|
| 697 |
-
"model.visual.blocks.7.attn.qkv.weight": "model-
|
| 698 |
-
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-
|
| 699 |
-
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-
|
| 700 |
-
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-
|
| 701 |
-
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-
|
| 702 |
-
"model.visual.blocks.7.norm1.bias": "model-
|
| 703 |
-
"model.visual.blocks.7.norm1.weight": "model-
|
| 704 |
-
"model.visual.blocks.7.norm2.bias": "model-
|
| 705 |
-
"model.visual.blocks.7.norm2.weight": "model-
|
| 706 |
-
"model.visual.blocks.8.attn.proj.bias": "model-
|
| 707 |
-
"model.visual.blocks.8.attn.proj.weight": "model-
|
| 708 |
-
"model.visual.blocks.8.attn.qkv.bias": "model-
|
| 709 |
-
"model.visual.blocks.8.attn.qkv.weight": "model-
|
| 710 |
-
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-
|
| 711 |
-
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-
|
| 712 |
-
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-
|
| 713 |
-
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-
|
| 714 |
-
"model.visual.blocks.8.norm1.bias": "model-
|
| 715 |
-
"model.visual.blocks.8.norm1.weight": "model-
|
| 716 |
-
"model.visual.blocks.8.norm2.bias": "model-
|
| 717 |
-
"model.visual.blocks.8.norm2.weight": "model-
|
| 718 |
-
"model.visual.blocks.9.attn.proj.bias": "model-
|
| 719 |
-
"model.visual.blocks.9.attn.proj.weight": "model-
|
| 720 |
-
"model.visual.blocks.9.attn.qkv.bias": "model-
|
| 721 |
-
"model.visual.blocks.9.attn.qkv.weight": "model-
|
| 722 |
-
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-
|
| 723 |
-
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-
|
| 724 |
-
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-
|
| 725 |
-
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-
|
| 726 |
-
"model.visual.blocks.9.norm1.bias": "model-
|
| 727 |
-
"model.visual.blocks.9.norm1.weight": "model-
|
| 728 |
-
"model.visual.blocks.9.norm2.bias": "model-
|
| 729 |
-
"model.visual.blocks.9.norm2.weight": "model-
|
| 730 |
-
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-
|
| 731 |
-
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-
|
| 732 |
-
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-
|
| 733 |
-
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-
|
| 734 |
-
"model.visual.deepstack_merger_list.0.norm.bias": "model-
|
| 735 |
-
"model.visual.deepstack_merger_list.0.norm.weight": "model-
|
| 736 |
-
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-
|
| 737 |
-
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-
|
| 738 |
-
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-
|
| 739 |
-
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-
|
| 740 |
-
"model.visual.deepstack_merger_list.1.norm.bias": "model-
|
| 741 |
-
"model.visual.deepstack_merger_list.1.norm.weight": "model-
|
| 742 |
-
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-
|
| 743 |
-
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-
|
| 744 |
-
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-
|
| 745 |
-
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-
|
| 746 |
-
"model.visual.deepstack_merger_list.2.norm.bias": "model-
|
| 747 |
-
"model.visual.deepstack_merger_list.2.norm.weight": "model-
|
| 748 |
-
"model.visual.merger.linear_fc1.bias": "model-
|
| 749 |
-
"model.visual.merger.linear_fc1.weight": "model-
|
| 750 |
-
"model.visual.merger.linear_fc2.bias": "model-
|
| 751 |
-
"model.visual.merger.linear_fc2.weight": "model-
|
| 752 |
-
"model.visual.merger.norm.bias": "model-
|
| 753 |
-
"model.visual.merger.norm.weight": "model-
|
| 754 |
-
"model.visual.patch_embed.proj.bias": "model-
|
| 755 |
-
"model.visual.patch_embed.proj.weight": "model-
|
| 756 |
-
"model.visual.pos_embed.weight": "model-
|
| 757 |
}
|
| 758 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
|
|
|
| 3 |
"total_size": 17534247392
|
| 4 |
},
|
| 5 |
"weight_map": {
|
|
|
|
| 126 |
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 127 |
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 134 |
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 136 |
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
|
|
|
| 148 |
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 149 |
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 150 |
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 174 |
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 185 |
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
|
|
|
| 291 |
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 292 |
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 293 |
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 299 |
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 301 |
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 303 |
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 304 |
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 328 |
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 329 |
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
|
|
|
| 331 |
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 332 |
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 337 |
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 339 |
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
|
|
|
| 357 |
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 358 |
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 359 |
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 362 |
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 365 |
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 367 |
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 369 |
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 370 |
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 394 |
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 396 |
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 405 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 409 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 413 |
+
"model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors",
|
| 417 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 421 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 425 |
+
"model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors",
|
| 429 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors",
|
| 729 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 730 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 731 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 732 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 733 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00004-of-00004.safetensors",
|
| 734 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00004-of-00004.safetensors",
|
| 735 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 736 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 737 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 738 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 739 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00004-of-00004.safetensors",
|
| 740 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00004-of-00004.safetensors",
|
| 741 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 742 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 743 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 744 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 745 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00004-of-00004.safetensors",
|
| 746 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00004-of-00004.safetensors",
|
| 747 |
+
"model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors",
|
| 748 |
+
"model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors",
|
| 749 |
+
"model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors",
|
| 750 |
+
"model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors",
|
| 751 |
+
"model.visual.merger.norm.bias": "model-00004-of-00004.safetensors",
|
| 752 |
+
"model.visual.merger.norm.weight": "model-00004-of-00004.safetensors",
|
| 753 |
+
"model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors",
|
| 754 |
+
"model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors",
|
| 755 |
+
"model.visual.pos_embed.weight": "model-00004-of-00004.safetensors"
|
| 756 |
}
|
| 757 |
}
|