Hugging Face's logo

deepseek-ai
/
Janus-Pro-7B

Any-to-Any
Transformers
PyTorch
multi_modality
muiltimodal
text-to-image
unified-model
Inference Endpoints
Model card Files Community
98
charlescxk commited on
Commit
55acc6e
·
1 Parent(s): 2493841

upload ckpt

Browse files
Files changed (12) hide show
  1. README.md +57 -0
  2. config.json +59 -0
  3. janus_pro_teaser1.png +0 -0
  4. janus_pro_teaser2.png +0 -0
  5. preprocessor_config.json +23 -0
  6. processor_config.json +9 -0
  7. pytorch_model-00001-of-00002.bin +3 -0
  8. pytorch_model-00002-of-00002.bin +3 -0
  9. pytorch_model.bin.index.json +943 -0
  10. special_tokens_map.json +16 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +10 -0
README.md CHANGED
@@ -1,3 +1,60 @@
1
  ---
2
  license: mit
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
+ license_name: deepseek
4
+ license_link: LICENSE
5
+ pipeline_tag: any-to-any
6
+ library_name: transformers
7
+ tags:
8
+ - muiltimodal
9
+ - text-to-image
10
+ - unified-model
11
  ---
12
+
13
+ ## 1. Introduction
14
+
15
+ Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation.
16
+ It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder’s roles in understanding and generation, but also enhances the framework’s flexibility.
17
+ Janus surpasses previous unified model and matches or exceeds the performance of task-specific models.
18
+ The simplicity, high flexibility, and effectiveness of Janus make it a strong candidate for next-generation unified multimodal models.
19
+
20
+ [**Github Repository**](https://github.com/deepseek-ai/Janus)
21
+
22
+ <div align="center">
23
+ <img alt="image" src="janus_pro_teaser1.png" style="width:90%;">
24
+ </div>
25
+
26
+ <div align="center">
27
+ <img alt="image" src="janus_pro_teaser2.png" style="width:90%;">
28
+ </div>
29
+
30
+
31
+ ### 2. Model Summary
32
+
33
+ Janus-Pro is a unified understanding and generation MLLM, which decouples visual encoding for multimodal understanding and generation.
34
+ Janus is constructed based on the DeepSeek-LLM-1.5b-base/DeepSeek-LLM-7b-base.
35
+
36
+ For multimodal understanding, it uses the [SigLIP-L](https://huggingface.co/timm/ViT-L-16-SigLIP-384) as the vision encoder, which supports 384 x 384 image input. For image generation, Janus uses the tokenizer from [here](https://github.com/FoundationVision/LlamaGen) with a downsample rate of 16.
37
+
38
+
39
+
40
+ ## 3. Quick Start
41
+
42
+ Please refer to [**Github Repository**](https://github.com/deepseek-ai/Janus)
43
+
44
+
45
+ ## 4. License
46
+
47
+ This code repository is licensed under [the MIT License](https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-CODE). The use of Janus models is subject to [DeepSeek Model License](https://github.com/deepseek-ai/DeepSeek-LLM/blob/HEAD/LICENSE-MODEL).
48
+ ## 5. Citation
49
+
50
+ ```
51
+ @misc{chen2025januspro,
52
+ title={Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling},
53
+ author={Xiaokang Chen and Zhiyu Wu and Xingchao Liu and Zizheng Pan and Wen Liu and Zhenda Xie and Xingkai Yu and Chong Ruan},
54
+ year={2025},
55
+ }
56
+ ```
57
+
58
+ ## 6. Contact
59
+
60
+ If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aligner_config": {
3
+ "cls": "MlpProjector",
4
+ "model_type": "aligner",
5
+ "params": {
6
+ "depth": 2,
7
+ "input_dim": 1024,
8
+ "n_embed": 4096,
9
+ "projector_type": "mlp_gelu"
10
+ }
11
+ },
12
+ "gen_aligner_config": {
13
+ "cls": "MlpProjector",
14
+ "model_type": "gen_aligner",
15
+ "params": {
16
+ "depth": 2,
17
+ "input_dim": 8,
18
+ "n_embed": 4096,
19
+ "projector_type": "mlp_gelu"
20
+ }
21
+ },
22
+ "gen_head_config": {
23
+ "cls": "vision_head",
24
+ "model_type": "gen_head",
25
+ "params": {
26
+ "image_token_embed": 4096,
27
+ "image_token_size": 16384,
28
+ "n_embed": 4096
29
+ }
30
+ },
31
+ "gen_vision_config": {
32
+ "cls": "VQ-16",
33
+ "model_type": "gen_vision",
34
+ "params": {
35
+ "image_token_size": 16384,
36
+ "n_embed": 8
37
+ }
38
+ },
39
+ "language_config": {
40
+ "max_position_embeddings": 16384,
41
+ "model_type": "llama",
42
+ "num_hidden_layers": 30,
43
+ "torch_dtype": "bfloat16",
44
+ "vocab_size": 102400
45
+ },
46
+ "model_type": "multi_modality",
47
+ "torch_dtype": "bfloat16",
48
+ "transformers_version": "4.33.1",
49
+ "vision_config": {
50
+ "cls": "CLIPVisionTower",
51
+ "model_type": "vision",
52
+ "params": {
53
+ "image_size": 384,
54
+ "model_name": "siglip_large_patch16_384",
55
+ "select_feature": "same",
56
+ "select_layer": -1
57
+ }
58
+ }
59
+ }
janus_pro_teaser1.png ADDED
janus_pro_teaser2.png ADDED
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "background_color": [
3
+ 127,
4
+ 127,
5
+ 127
6
+ ],
7
+ "do_normalize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "VLMImageProcessor",
14
+ "image_size": 384,
15
+ "image_std": [
16
+ 0.5,
17
+ 0.5,
18
+ 0.5
19
+ ],
20
+ "min_size": 14,
21
+ "processor_class": "VLChatProcessor",
22
+ "rescale_factor": 0.00392156862745098
23
+ }
processor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_special_token": false,
3
+ "ignore_id": -100,
4
+ "image_tag": "<image_placeholder>",
5
+ "mask_prompt": true,
6
+ "num_image_tokens": 576,
7
+ "processor_class": "VLChatProcessor",
8
+ "sft_format": "deepseek"
9
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c90acffa3b3eeea5dff0451f4752d2cddca14a50f906ba1eaa7591895c197ec
3
+ size 9988183802
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb7c7d12c16933f519f4959cbc8514bb50561f2945069f6d3b5827aadaac800
3
+ size 4853013705
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,943 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14840868118
4
+ },
5
+ "weight_map": {
6
+ "aligner.layers.0.bias": "pytorch_model-00001-of-00002.bin",
7
+ "aligner.layers.0.weight": "pytorch_model-00001-of-00002.bin",
8
+ "aligner.layers.2.bias": "pytorch_model-00001-of-00002.bin",
9
+ "aligner.layers.2.weight": "pytorch_model-00001-of-00002.bin",
10
+ "gen_aligner.layers.0.bias": "pytorch_model-00001-of-00002.bin",
11
+ "gen_aligner.layers.0.weight": "pytorch_model-00001-of-00002.bin",
12
+ "gen_aligner.layers.2.bias": "pytorch_model-00001-of-00002.bin",
13
+ "gen_aligner.layers.2.weight": "pytorch_model-00001-of-00002.bin",
14
+ "gen_embed.weight": "pytorch_model-00001-of-00002.bin",
15
+ "gen_head.output_mlp_projector.bias": "pytorch_model-00001-of-00002.bin",
16
+ "gen_head.output_mlp_projector.weight": "pytorch_model-00001-of-00002.bin",
17
+ "gen_head.vision_head.bias": "pytorch_model-00001-of-00002.bin",
18
+ "gen_head.vision_head.weight": "pytorch_model-00001-of-00002.bin",
19
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.k.bias": "pytorch_model-00001-of-00002.bin",
20
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.k.weight": "pytorch_model-00001-of-00002.bin",
21
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.norm.bias": "pytorch_model-00001-of-00002.bin",
22
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.norm.weight": "pytorch_model-00001-of-00002.bin",
23
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.proj_out.bias": "pytorch_model-00001-of-00002.bin",
24
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.proj_out.weight": "pytorch_model-00001-of-00002.bin",
25
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.q.bias": "pytorch_model-00001-of-00002.bin",
26
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.q.weight": "pytorch_model-00001-of-00002.bin",
27
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.v.bias": "pytorch_model-00001-of-00002.bin",
28
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.v.weight": "pytorch_model-00001-of-00002.bin",
29
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.k.bias": "pytorch_model-00001-of-00002.bin",
30
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.k.weight": "pytorch_model-00001-of-00002.bin",
31
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.norm.bias": "pytorch_model-00001-of-00002.bin",
32
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.norm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.proj_out.bias": "pytorch_model-00001-of-00002.bin",
34
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.proj_out.weight": "pytorch_model-00001-of-00002.bin",
35
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.q.bias": "pytorch_model-00001-of-00002.bin",
36
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.q.weight": "pytorch_model-00001-of-00002.bin",
37
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.v.bias": "pytorch_model-00001-of-00002.bin",
38
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.v.weight": "pytorch_model-00001-of-00002.bin",
39
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.k.bias": "pytorch_model-00001-of-00002.bin",
40
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.k.weight": "pytorch_model-00001-of-00002.bin",
41
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.norm.bias": "pytorch_model-00001-of-00002.bin",
42
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.norm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.proj_out.bias": "pytorch_model-00001-of-00002.bin",
44
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.proj_out.weight": "pytorch_model-00001-of-00002.bin",
45
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.q.bias": "pytorch_model-00001-of-00002.bin",
46
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.q.weight": "pytorch_model-00001-of-00002.bin",
47
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.v.bias": "pytorch_model-00001-of-00002.bin",
48
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.v.weight": "pytorch_model-00001-of-00002.bin",
49
+ "gen_vision_model.decoder.conv_blocks.0.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
50
+ "gen_vision_model.decoder.conv_blocks.0.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
51
+ "gen_vision_model.decoder.conv_blocks.0.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
52
+ "gen_vision_model.decoder.conv_blocks.0.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
53
+ "gen_vision_model.decoder.conv_blocks.0.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
54
+ "gen_vision_model.decoder.conv_blocks.0.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
55
+ "gen_vision_model.decoder.conv_blocks.0.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
56
+ "gen_vision_model.decoder.conv_blocks.0.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
57
+ "gen_vision_model.decoder.conv_blocks.0.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
58
+ "gen_vision_model.decoder.conv_blocks.0.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
59
+ "gen_vision_model.decoder.conv_blocks.0.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
60
+ "gen_vision_model.decoder.conv_blocks.0.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
61
+ "gen_vision_model.decoder.conv_blocks.0.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
62
+ "gen_vision_model.decoder.conv_blocks.0.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
63
+ "gen_vision_model.decoder.conv_blocks.0.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
64
+ "gen_vision_model.decoder.conv_blocks.0.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
65
+ "gen_vision_model.decoder.conv_blocks.0.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
66
+ "gen_vision_model.decoder.conv_blocks.0.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
67
+ "gen_vision_model.decoder.conv_blocks.0.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
68
+ "gen_vision_model.decoder.conv_blocks.0.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
69
+ "gen_vision_model.decoder.conv_blocks.0.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
70
+ "gen_vision_model.decoder.conv_blocks.0.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
71
+ "gen_vision_model.decoder.conv_blocks.0.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
72
+ "gen_vision_model.decoder.conv_blocks.0.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
73
+ "gen_vision_model.decoder.conv_blocks.0.upsample.conv.bias": "pytorch_model-00001-of-00002.bin",
74
+ "gen_vision_model.decoder.conv_blocks.0.upsample.conv.weight": "pytorch_model-00001-of-00002.bin",
75
+ "gen_vision_model.decoder.conv_blocks.1.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
76
+ "gen_vision_model.decoder.conv_blocks.1.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
77
+ "gen_vision_model.decoder.conv_blocks.1.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
78
+ "gen_vision_model.decoder.conv_blocks.1.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
79
+ "gen_vision_model.decoder.conv_blocks.1.res.0.nin_shortcut.bias": "pytorch_model-00001-of-00002.bin",
80
+ "gen_vision_model.decoder.conv_blocks.1.res.0.nin_shortcut.weight": "pytorch_model-00001-of-00002.bin",
81
+ "gen_vision_model.decoder.conv_blocks.1.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
82
+ "gen_vision_model.decoder.conv_blocks.1.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
83
+ "gen_vision_model.decoder.conv_blocks.1.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
84
+ "gen_vision_model.decoder.conv_blocks.1.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
85
+ "gen_vision_model.decoder.conv_blocks.1.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
86
+ "gen_vision_model.decoder.conv_blocks.1.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
87
+ "gen_vision_model.decoder.conv_blocks.1.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
88
+ "gen_vision_model.decoder.conv_blocks.1.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
89
+ "gen_vision_model.decoder.conv_blocks.1.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
90
+ "gen_vision_model.decoder.conv_blocks.1.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
91
+ "gen_vision_model.decoder.conv_blocks.1.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
92
+ "gen_vision_model.decoder.conv_blocks.1.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
93
+ "gen_vision_model.decoder.conv_blocks.1.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
94
+ "gen_vision_model.decoder.conv_blocks.1.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
95
+ "gen_vision_model.decoder.conv_blocks.1.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
96
+ "gen_vision_model.decoder.conv_blocks.1.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
97
+ "gen_vision_model.decoder.conv_blocks.1.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
98
+ "gen_vision_model.decoder.conv_blocks.1.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
99
+ "gen_vision_model.decoder.conv_blocks.1.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
100
+ "gen_vision_model.decoder.conv_blocks.1.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
101
+ "gen_vision_model.decoder.conv_blocks.1.upsample.conv.bias": "pytorch_model-00001-of-00002.bin",
102
+ "gen_vision_model.decoder.conv_blocks.1.upsample.conv.weight": "pytorch_model-00001-of-00002.bin",
103
+ "gen_vision_model.decoder.conv_blocks.2.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
104
+ "gen_vision_model.decoder.conv_blocks.2.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
105
+ "gen_vision_model.decoder.conv_blocks.2.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
106
+ "gen_vision_model.decoder.conv_blocks.2.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
107
+ "gen_vision_model.decoder.conv_blocks.2.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
108
+ "gen_vision_model.decoder.conv_blocks.2.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
109
+ "gen_vision_model.decoder.conv_blocks.2.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
110
+ "gen_vision_model.decoder.conv_blocks.2.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
111
+ "gen_vision_model.decoder.conv_blocks.2.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
112
+ "gen_vision_model.decoder.conv_blocks.2.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
113
+ "gen_vision_model.decoder.conv_blocks.2.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
114
+ "gen_vision_model.decoder.conv_blocks.2.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
115
+ "gen_vision_model.decoder.conv_blocks.2.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
116
+ "gen_vision_model.decoder.conv_blocks.2.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
117
+ "gen_vision_model.decoder.conv_blocks.2.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
118
+ "gen_vision_model.decoder.conv_blocks.2.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
119
+ "gen_vision_model.decoder.conv_blocks.2.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
120
+ "gen_vision_model.decoder.conv_blocks.2.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
121
+ "gen_vision_model.decoder.conv_blocks.2.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
122
+ "gen_vision_model.decoder.conv_blocks.2.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
123
+ "gen_vision_model.decoder.conv_blocks.2.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
124
+ "gen_vision_model.decoder.conv_blocks.2.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
125
+ "gen_vision_model.decoder.conv_blocks.2.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
126
+ "gen_vision_model.decoder.conv_blocks.2.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
127
+ "gen_vision_model.decoder.conv_blocks.2.upsample.conv.bias": "pytorch_model-00001-of-00002.bin",
128
+ "gen_vision_model.decoder.conv_blocks.2.upsample.conv.weight": "pytorch_model-00001-of-00002.bin",
129
+ "gen_vision_model.decoder.conv_blocks.3.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
130
+ "gen_vision_model.decoder.conv_blocks.3.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
131
+ "gen_vision_model.decoder.conv_blocks.3.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
132
+ "gen_vision_model.decoder.conv_blocks.3.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
133
+ "gen_vision_model.decoder.conv_blocks.3.res.0.nin_shortcut.bias": "pytorch_model-00001-of-00002.bin",
134
+ "gen_vision_model.decoder.conv_blocks.3.res.0.nin_shortcut.weight": "pytorch_model-00001-of-00002.bin",
135
+ "gen_vision_model.decoder.conv_blocks.3.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
136
+ "gen_vision_model.decoder.conv_blocks.3.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
137
+ "gen_vision_model.decoder.conv_blocks.3.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
138
+ "gen_vision_model.decoder.conv_blocks.3.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
139
+ "gen_vision_model.decoder.conv_blocks.3.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
140
+ "gen_vision_model.decoder.conv_blocks.3.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
141
+ "gen_vision_model.decoder.conv_blocks.3.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
142
+ "gen_vision_model.decoder.conv_blocks.3.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
143
+ "gen_vision_model.decoder.conv_blocks.3.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
144
+ "gen_vision_model.decoder.conv_blocks.3.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
145
+ "gen_vision_model.decoder.conv_blocks.3.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
146
+ "gen_vision_model.decoder.conv_blocks.3.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
147
+ "gen_vision_model.decoder.conv_blocks.3.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
148
+ "gen_vision_model.decoder.conv_blocks.3.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
149
+ "gen_vision_model.decoder.conv_blocks.3.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
150
+ "gen_vision_model.decoder.conv_blocks.3.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
151
+ "gen_vision_model.decoder.conv_blocks.3.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
152
+ "gen_vision_model.decoder.conv_blocks.3.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
153
+ "gen_vision_model.decoder.conv_blocks.3.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
154
+ "gen_vision_model.decoder.conv_blocks.3.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
155
+ "gen_vision_model.decoder.conv_blocks.3.upsample.conv.bias": "pytorch_model-00001-of-00002.bin",
156
+ "gen_vision_model.decoder.conv_blocks.3.upsample.conv.weight": "pytorch_model-00001-of-00002.bin",
157
+ "gen_vision_model.decoder.conv_blocks.4.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
158
+ "gen_vision_model.decoder.conv_blocks.4.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
159
+ "gen_vision_model.decoder.conv_blocks.4.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
160
+ "gen_vision_model.decoder.conv_blocks.4.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
161
+ "gen_vision_model.decoder.conv_blocks.4.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
162
+ "gen_vision_model.decoder.conv_blocks.4.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
163
+ "gen_vision_model.decoder.conv_blocks.4.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
164
+ "gen_vision_model.decoder.conv_blocks.4.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
165
+ "gen_vision_model.decoder.conv_blocks.4.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
166
+ "gen_vision_model.decoder.conv_blocks.4.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
167
+ "gen_vision_model.decoder.conv_blocks.4.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
168
+ "gen_vision_model.decoder.conv_blocks.4.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
169
+ "gen_vision_model.decoder.conv_blocks.4.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
170
+ "gen_vision_model.decoder.conv_blocks.4.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
171
+ "gen_vision_model.decoder.conv_blocks.4.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
172
+ "gen_vision_model.decoder.conv_blocks.4.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
173
+ "gen_vision_model.decoder.conv_blocks.4.res.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
174
+ "gen_vision_model.decoder.conv_blocks.4.res.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
175
+ "gen_vision_model.decoder.conv_blocks.4.res.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
176
+ "gen_vision_model.decoder.conv_blocks.4.res.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
177
+ "gen_vision_model.decoder.conv_blocks.4.res.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
178
+ "gen_vision_model.decoder.conv_blocks.4.res.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
179
+ "gen_vision_model.decoder.conv_blocks.4.res.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
180
+ "gen_vision_model.decoder.conv_blocks.4.res.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
181
+ "gen_vision_model.decoder.conv_in.bias": "pytorch_model-00001-of-00002.bin",
182
+ "gen_vision_model.decoder.conv_in.weight": "pytorch_model-00001-of-00002.bin",
183
+ "gen_vision_model.decoder.conv_out.bias": "pytorch_model-00001-of-00002.bin",
184
+ "gen_vision_model.decoder.conv_out.weight": "pytorch_model-00001-of-00002.bin",
185
+ "gen_vision_model.decoder.mid.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
186
+ "gen_vision_model.decoder.mid.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
187
+ "gen_vision_model.decoder.mid.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
188
+ "gen_vision_model.decoder.mid.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
189
+ "gen_vision_model.decoder.mid.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
190
+ "gen_vision_model.decoder.mid.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
191
+ "gen_vision_model.decoder.mid.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
192
+ "gen_vision_model.decoder.mid.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
193
+ "gen_vision_model.decoder.mid.1.k.bias": "pytorch_model-00001-of-00002.bin",
194
+ "gen_vision_model.decoder.mid.1.k.weight": "pytorch_model-00001-of-00002.bin",
195
+ "gen_vision_model.decoder.mid.1.norm.bias": "pytorch_model-00001-of-00002.bin",
196
+ "gen_vision_model.decoder.mid.1.norm.weight": "pytorch_model-00001-of-00002.bin",
197
+ "gen_vision_model.decoder.mid.1.proj_out.bias": "pytorch_model-00001-of-00002.bin",
198
+ "gen_vision_model.decoder.mid.1.proj_out.weight": "pytorch_model-00001-of-00002.bin",
199
+ "gen_vision_model.decoder.mid.1.q.bias": "pytorch_model-00001-of-00002.bin",
200
+ "gen_vision_model.decoder.mid.1.q.weight": "pytorch_model-00001-of-00002.bin",
201
+ "gen_vision_model.decoder.mid.1.v.bias": "pytorch_model-00001-of-00002.bin",
202
+ "gen_vision_model.decoder.mid.1.v.weight": "pytorch_model-00001-of-00002.bin",
203
+ "gen_vision_model.decoder.mid.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
204
+ "gen_vision_model.decoder.mid.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
205
+ "gen_vision_model.decoder.mid.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
206
+ "gen_vision_model.decoder.mid.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
207
+ "gen_vision_model.decoder.mid.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
208
+ "gen_vision_model.decoder.mid.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
209
+ "gen_vision_model.decoder.mid.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
210
+ "gen_vision_model.decoder.mid.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
211
+ "gen_vision_model.decoder.norm_out.bias": "pytorch_model-00001-of-00002.bin",
212
+ "gen_vision_model.decoder.norm_out.weight": "pytorch_model-00001-of-00002.bin",
213
+ "gen_vision_model.encoder.conv_blocks.0.downsample.conv.bias": "pytorch_model-00001-of-00002.bin",
214
+ "gen_vision_model.encoder.conv_blocks.0.downsample.conv.weight": "pytorch_model-00001-of-00002.bin",
215
+ "gen_vision_model.encoder.conv_blocks.0.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
216
+ "gen_vision_model.encoder.conv_blocks.0.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
217
+ "gen_vision_model.encoder.conv_blocks.0.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
218
+ "gen_vision_model.encoder.conv_blocks.0.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
219
+ "gen_vision_model.encoder.conv_blocks.0.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
220
+ "gen_vision_model.encoder.conv_blocks.0.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
221
+ "gen_vision_model.encoder.conv_blocks.0.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
222
+ "gen_vision_model.encoder.conv_blocks.0.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
223
+ "gen_vision_model.encoder.conv_blocks.0.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
224
+ "gen_vision_model.encoder.conv_blocks.0.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
225
+ "gen_vision_model.encoder.conv_blocks.0.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
226
+ "gen_vision_model.encoder.conv_blocks.0.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
227
+ "gen_vision_model.encoder.conv_blocks.0.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
228
+ "gen_vision_model.encoder.conv_blocks.0.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
229
+ "gen_vision_model.encoder.conv_blocks.0.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
230
+ "gen_vision_model.encoder.conv_blocks.0.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
231
+ "gen_vision_model.encoder.conv_blocks.1.downsample.conv.bias": "pytorch_model-00001-of-00002.bin",
232
+ "gen_vision_model.encoder.conv_blocks.1.downsample.conv.weight": "pytorch_model-00001-of-00002.bin",
233
+ "gen_vision_model.encoder.conv_blocks.1.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
234
+ "gen_vision_model.encoder.conv_blocks.1.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
235
+ "gen_vision_model.encoder.conv_blocks.1.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
236
+ "gen_vision_model.encoder.conv_blocks.1.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
237
+ "gen_vision_model.encoder.conv_blocks.1.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
238
+ "gen_vision_model.encoder.conv_blocks.1.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
239
+ "gen_vision_model.encoder.conv_blocks.1.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
240
+ "gen_vision_model.encoder.conv_blocks.1.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
241
+ "gen_vision_model.encoder.conv_blocks.1.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
242
+ "gen_vision_model.encoder.conv_blocks.1.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
243
+ "gen_vision_model.encoder.conv_blocks.1.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
244
+ "gen_vision_model.encoder.conv_blocks.1.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
245
+ "gen_vision_model.encoder.conv_blocks.1.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
246
+ "gen_vision_model.encoder.conv_blocks.1.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
247
+ "gen_vision_model.encoder.conv_blocks.1.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
248
+ "gen_vision_model.encoder.conv_blocks.1.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
249
+ "gen_vision_model.encoder.conv_blocks.2.downsample.conv.bias": "pytorch_model-00001-of-00002.bin",
250
+ "gen_vision_model.encoder.conv_blocks.2.downsample.conv.weight": "pytorch_model-00001-of-00002.bin",
251
+ "gen_vision_model.encoder.conv_blocks.2.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
252
+ "gen_vision_model.encoder.conv_blocks.2.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
253
+ "gen_vision_model.encoder.conv_blocks.2.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
254
+ "gen_vision_model.encoder.conv_blocks.2.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
255
+ "gen_vision_model.encoder.conv_blocks.2.res.0.nin_shortcut.bias": "pytorch_model-00001-of-00002.bin",
256
+ "gen_vision_model.encoder.conv_blocks.2.res.0.nin_shortcut.weight": "pytorch_model-00001-of-00002.bin",
257
+ "gen_vision_model.encoder.conv_blocks.2.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
258
+ "gen_vision_model.encoder.conv_blocks.2.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
259
+ "gen_vision_model.encoder.conv_blocks.2.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
260
+ "gen_vision_model.encoder.conv_blocks.2.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
261
+ "gen_vision_model.encoder.conv_blocks.2.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
262
+ "gen_vision_model.encoder.conv_blocks.2.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
263
+ "gen_vision_model.encoder.conv_blocks.2.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
264
+ "gen_vision_model.encoder.conv_blocks.2.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
265
+ "gen_vision_model.encoder.conv_blocks.2.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
266
+ "gen_vision_model.encoder.conv_blocks.2.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
267
+ "gen_vision_model.encoder.conv_blocks.2.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
268
+ "gen_vision_model.encoder.conv_blocks.2.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
269
+ "gen_vision_model.encoder.conv_blocks.3.downsample.conv.bias": "pytorch_model-00001-of-00002.bin",
270
+ "gen_vision_model.encoder.conv_blocks.3.downsample.conv.weight": "pytorch_model-00001-of-00002.bin",
271
+ "gen_vision_model.encoder.conv_blocks.3.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
272
+ "gen_vision_model.encoder.conv_blocks.3.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
273
+ "gen_vision_model.encoder.conv_blocks.3.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
274
+ "gen_vision_model.encoder.conv_blocks.3.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
275
+ "gen_vision_model.encoder.conv_blocks.3.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
276
+ "gen_vision_model.encoder.conv_blocks.3.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
277
+ "gen_vision_model.encoder.conv_blocks.3.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
278
+ "gen_vision_model.encoder.conv_blocks.3.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
279
+ "gen_vision_model.encoder.conv_blocks.3.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
280
+ "gen_vision_model.encoder.conv_blocks.3.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
281
+ "gen_vision_model.encoder.conv_blocks.3.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
282
+ "gen_vision_model.encoder.conv_blocks.3.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
283
+ "gen_vision_model.encoder.conv_blocks.3.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
284
+ "gen_vision_model.encoder.conv_blocks.3.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
285
+ "gen_vision_model.encoder.conv_blocks.3.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
286
+ "gen_vision_model.encoder.conv_blocks.3.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
287
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.k.bias": "pytorch_model-00001-of-00002.bin",
288
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.k.weight": "pytorch_model-00001-of-00002.bin",
289
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.norm.bias": "pytorch_model-00001-of-00002.bin",
290
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.norm.weight": "pytorch_model-00001-of-00002.bin",
291
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.proj_out.bias": "pytorch_model-00001-of-00002.bin",
292
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.proj_out.weight": "pytorch_model-00001-of-00002.bin",
293
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.q.bias": "pytorch_model-00001-of-00002.bin",
294
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.q.weight": "pytorch_model-00001-of-00002.bin",
295
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.v.bias": "pytorch_model-00001-of-00002.bin",
296
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.v.weight": "pytorch_model-00001-of-00002.bin",
297
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.k.bias": "pytorch_model-00001-of-00002.bin",
298
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.k.weight": "pytorch_model-00001-of-00002.bin",
299
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.norm.bias": "pytorch_model-00001-of-00002.bin",
300
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.norm.weight": "pytorch_model-00001-of-00002.bin",
301
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.proj_out.bias": "pytorch_model-00001-of-00002.bin",
302
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.proj_out.weight": "pytorch_model-00001-of-00002.bin",
303
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.q.bias": "pytorch_model-00001-of-00002.bin",
304
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.q.weight": "pytorch_model-00001-of-00002.bin",
305
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.v.bias": "pytorch_model-00001-of-00002.bin",
306
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.v.weight": "pytorch_model-00001-of-00002.bin",
307
+ "gen_vision_model.encoder.conv_blocks.4.res.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
308
+ "gen_vision_model.encoder.conv_blocks.4.res.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
309
+ "gen_vision_model.encoder.conv_blocks.4.res.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
310
+ "gen_vision_model.encoder.conv_blocks.4.res.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
311
+ "gen_vision_model.encoder.conv_blocks.4.res.0.nin_shortcut.bias": "pytorch_model-00001-of-00002.bin",
312
+ "gen_vision_model.encoder.conv_blocks.4.res.0.nin_shortcut.weight": "pytorch_model-00001-of-00002.bin",
313
+ "gen_vision_model.encoder.conv_blocks.4.res.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
314
+ "gen_vision_model.encoder.conv_blocks.4.res.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
315
+ "gen_vision_model.encoder.conv_blocks.4.res.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
316
+ "gen_vision_model.encoder.conv_blocks.4.res.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
317
+ "gen_vision_model.encoder.conv_blocks.4.res.1.conv1.bias": "pytorch_model-00001-of-00002.bin",
318
+ "gen_vision_model.encoder.conv_blocks.4.res.1.conv1.weight": "pytorch_model-00001-of-00002.bin",
319
+ "gen_vision_model.encoder.conv_blocks.4.res.1.conv2.bias": "pytorch_model-00001-of-00002.bin",
320
+ "gen_vision_model.encoder.conv_blocks.4.res.1.conv2.weight": "pytorch_model-00001-of-00002.bin",
321
+ "gen_vision_model.encoder.conv_blocks.4.res.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
322
+ "gen_vision_model.encoder.conv_blocks.4.res.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
323
+ "gen_vision_model.encoder.conv_blocks.4.res.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
324
+ "gen_vision_model.encoder.conv_blocks.4.res.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
325
+ "gen_vision_model.encoder.conv_in.bias": "pytorch_model-00001-of-00002.bin",
326
+ "gen_vision_model.encoder.conv_in.weight": "pytorch_model-00001-of-00002.bin",
327
+ "gen_vision_model.encoder.conv_out.bias": "pytorch_model-00001-of-00002.bin",
328
+ "gen_vision_model.encoder.conv_out.weight": "pytorch_model-00001-of-00002.bin",
329
+ "gen_vision_model.encoder.mid.0.conv1.bias": "pytorch_model-00001-of-00002.bin",
330
+ "gen_vision_model.encoder.mid.0.conv1.weight": "pytorch_model-00001-of-00002.bin",
331
+ "gen_vision_model.encoder.mid.0.conv2.bias": "pytorch_model-00001-of-00002.bin",
332
+ "gen_vision_model.encoder.mid.0.conv2.weight": "pytorch_model-00001-of-00002.bin",
333
+ "gen_vision_model.encoder.mid.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
334
+ "gen_vision_model.encoder.mid.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
335
+ "gen_vision_model.encoder.mid.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
336
+ "gen_vision_model.encoder.mid.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
337
+ "gen_vision_model.encoder.mid.1.k.bias": "pytorch_model-00001-of-00002.bin",
338
+ "gen_vision_model.encoder.mid.1.k.weight": "pytorch_model-00001-of-00002.bin",
339
+ "gen_vision_model.encoder.mid.1.norm.bias": "pytorch_model-00001-of-00002.bin",
340
+ "gen_vision_model.encoder.mid.1.norm.weight": "pytorch_model-00001-of-00002.bin",
341
+ "gen_vision_model.encoder.mid.1.proj_out.bias": "pytorch_model-00001-of-00002.bin",
342
+ "gen_vision_model.encoder.mid.1.proj_out.weight": "pytorch_model-00001-of-00002.bin",
343
+ "gen_vision_model.encoder.mid.1.q.bias": "pytorch_model-00001-of-00002.bin",
344
+ "gen_vision_model.encoder.mid.1.q.weight": "pytorch_model-00001-of-00002.bin",
345
+ "gen_vision_model.encoder.mid.1.v.bias": "pytorch_model-00001-of-00002.bin",
346
+ "gen_vision_model.encoder.mid.1.v.weight": "pytorch_model-00001-of-00002.bin",
347
+ "gen_vision_model.encoder.mid.2.conv1.bias": "pytorch_model-00001-of-00002.bin",
348
+ "gen_vision_model.encoder.mid.2.conv1.weight": "pytorch_model-00001-of-00002.bin",
349
+ "gen_vision_model.encoder.mid.2.conv2.bias": "pytorch_model-00001-of-00002.bin",
350
+ "gen_vision_model.encoder.mid.2.conv2.weight": "pytorch_model-00001-of-00002.bin",
351
+ "gen_vision_model.encoder.mid.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
352
+ "gen_vision_model.encoder.mid.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
353
+ "gen_vision_model.encoder.mid.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
354
+ "gen_vision_model.encoder.mid.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
355
+ "gen_vision_model.encoder.norm_out.bias": "pytorch_model-00001-of-00002.bin",
356
+ "gen_vision_model.encoder.norm_out.weight": "pytorch_model-00001-of-00002.bin",
357
+ "gen_vision_model.post_quant_conv.bias": "pytorch_model-00001-of-00002.bin",
358
+ "gen_vision_model.post_quant_conv.weight": "pytorch_model-00001-of-00002.bin",
359
+ "gen_vision_model.quant_conv.bias": "pytorch_model-00001-of-00002.bin",
360
+ "gen_vision_model.quant_conv.weight": "pytorch_model-00001-of-00002.bin",
361
+ "gen_vision_model.quantize.codebook_used": "pytorch_model-00001-of-00002.bin",
362
+ "gen_vision_model.quantize.embedding.weight": "pytorch_model-00001-of-00002.bin",
363
+ "language_model.lm_head.weight": "pytorch_model-00002-of-00002.bin",
364
+ "language_model.model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
365
+ "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
366
+ "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
367
+ "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
368
+ "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
369
+ "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
370
+ "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
371
+ "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
372
+ "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
373
+ "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
374
+ "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
375
+ "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
376
+ "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
377
+ "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
378
+ "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
379
+ "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
380
+ "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
381
+ "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
382
+ "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
383
+ "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
384
+ "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
385
+ "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
386
+ "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
387
+ "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
388
+ "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
389
+ "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
390
+ "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
391
+ "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
392
+ "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
393
+ "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
394
+ "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
395
+ "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
396
+ "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
397
+ "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
398
+ "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
399
+ "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
400
+ "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
401
+ "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
402
+ "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
403
+ "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
404
+ "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
405
+ "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
406
+ "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
407
+ "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
408
+ "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
409
+ "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
410
+ "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
411
+ "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
412
+ "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
413
+ "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
414
+ "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
415
+ "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
416
+ "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
417
+ "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
418
+ "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
419
+ "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
420
+ "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
421
+ "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
422
+ "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
423
+ "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
424
+ "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
425
+ "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
426
+ "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
427
+ "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
428
+ "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
429
+ "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
430
+ "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
431
+ "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
432
+ "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
433
+ "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
434
+ "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
435
+ "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
436
+ "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
437
+ "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
438
+ "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
439
+ "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
440
+ "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
441
+ "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
442
+ "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
443
+ "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
444
+ "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
445
+ "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
446
+ "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
447
+ "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
448
+ "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
449
+ "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
450
+ "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
451
+ "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
452
+ "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
453
+ "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
454
+ "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
455
+ "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
456
+ "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
457
+ "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
458
+ "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
459
+ "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
460
+ "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
461
+ "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
462
+ "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
463
+ "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
464
+ "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
465
+ "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
466
+ "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
467
+ "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
468
+ "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
469
+ "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
470
+ "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
471
+ "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
472
+ "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
473
+ "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
474
+ "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
475
+ "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
476
+ "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
477
+ "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
478
+ "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
479
+ "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
480
+ "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
481
+ "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
482
+ "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
483
+ "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
484
+ "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
485
+ "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
486
+ "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
487
+ "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
488
+ "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
489
+ "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
490
+ "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
491
+ "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
492
+ "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
493
+ "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
494
+ "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
495
+ "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
496
+ "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
497
+ "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
498
+ "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
499
+ "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
500
+ "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
501
+ "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
502
+ "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
503
+ "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
504
+ "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
505
+ "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
506
+ "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
507
+ "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
508
+ "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
509
+ "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
510
+ "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
511
+ "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
512
+ "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
513
+ "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
514
+ "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
515
+ "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
516
+ "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
517
+ "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
518
+ "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
519
+ "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
520
+ "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
521
+ "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
522
+ "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
523
+ "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
524
+ "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
525
+ "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
526
+ "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
527
+ "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
528
+ "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
529
+ "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
530
+ "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
531
+ "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
532
+ "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
533
+ "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
534
+ "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
535
+ "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
536
+ "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
537
+ "language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
538
+ "language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
539
+ "language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
540
+ "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
541
+ "language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
542
+ "language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
543
+ "language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
544
+ "language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
545
+ "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
546
+ "language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
547
+ "language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
548
+ "language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
549
+ "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
550
+ "language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
551
+ "language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
552
+ "language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
553
+ "language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
554
+ "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
555
+ "language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
556
+ "language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
557
+ "language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
558
+ "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
559
+ "language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
560
+ "language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
561
+ "language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
562
+ "language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
563
+ "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
564
+ "language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
565
+ "language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
566
+ "language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
567
+ "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
568
+ "language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
569
+ "language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
570
+ "language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
571
+ "language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
572
+ "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
573
+ "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
574
+ "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
575
+ "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
576
+ "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
577
+ "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
578
+ "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
579
+ "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
580
+ "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
581
+ "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
582
+ "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
583
+ "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
584
+ "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
585
+ "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
586
+ "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
587
+ "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
588
+ "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
589
+ "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
590
+ "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
591
+ "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
592
+ "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
593
+ "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
594
+ "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
595
+ "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
596
+ "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
597
+ "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
598
+ "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
599
+ "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
600
+ "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
601
+ "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
602
+ "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
603
+ "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
604
+ "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
605
+ "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
606
+ "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
607
+ "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
608
+ "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
609
+ "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
610
+ "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
611
+ "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
612
+ "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
613
+ "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
614
+ "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
615
+ "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
616
+ "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
617
+ "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
618
+ "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
619
+ "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
620
+ "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
621
+ "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
622
+ "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
623
+ "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
624
+ "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
625
+ "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
626
+ "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
627
+ "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
628
+ "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
629
+ "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
630
+ "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
631
+ "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
632
+ "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
633
+ "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
634
+ "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
635
+ "language_model.model.norm.weight": "pytorch_model-00002-of-00002.bin",
636
+ "vision_model.vision_tower.attn_pool.kv.bias": "pytorch_model-00001-of-00002.bin",
637
+ "vision_model.vision_tower.attn_pool.kv.weight": "pytorch_model-00001-of-00002.bin",
638
+ "vision_model.vision_tower.attn_pool.latent": "pytorch_model-00001-of-00002.bin",
639
+ "vision_model.vision_tower.attn_pool.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
640
+ "vision_model.vision_tower.attn_pool.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
641
+ "vision_model.vision_tower.attn_pool.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
642
+ "vision_model.vision_tower.attn_pool.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
643
+ "vision_model.vision_tower.attn_pool.norm.bias": "pytorch_model-00001-of-00002.bin",
644
+ "vision_model.vision_tower.attn_pool.norm.weight": "pytorch_model-00001-of-00002.bin",
645
+ "vision_model.vision_tower.attn_pool.proj.bias": "pytorch_model-00001-of-00002.bin",
646
+ "vision_model.vision_tower.attn_pool.proj.weight": "pytorch_model-00001-of-00002.bin",
647
+ "vision_model.vision_tower.attn_pool.q.bias": "pytorch_model-00001-of-00002.bin",
648
+ "vision_model.vision_tower.attn_pool.q.weight": "pytorch_model-00001-of-00002.bin",
649
+ "vision_model.vision_tower.blocks.0.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
650
+ "vision_model.vision_tower.blocks.0.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
651
+ "vision_model.vision_tower.blocks.0.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
652
+ "vision_model.vision_tower.blocks.0.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
653
+ "vision_model.vision_tower.blocks.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
654
+ "vision_model.vision_tower.blocks.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
655
+ "vision_model.vision_tower.blocks.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
656
+ "vision_model.vision_tower.blocks.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
657
+ "vision_model.vision_tower.blocks.0.norm1.bias": "pytorch_model-00001-of-00002.bin",
658
+ "vision_model.vision_tower.blocks.0.norm1.weight": "pytorch_model-00001-of-00002.bin",
659
+ "vision_model.vision_tower.blocks.0.norm2.bias": "pytorch_model-00001-of-00002.bin",
660
+ "vision_model.vision_tower.blocks.0.norm2.weight": "pytorch_model-00001-of-00002.bin",
661
+ "vision_model.vision_tower.blocks.1.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
662
+ "vision_model.vision_tower.blocks.1.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
663
+ "vision_model.vision_tower.blocks.1.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
664
+ "vision_model.vision_tower.blocks.1.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
665
+ "vision_model.vision_tower.blocks.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
666
+ "vision_model.vision_tower.blocks.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
667
+ "vision_model.vision_tower.blocks.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
668
+ "vision_model.vision_tower.blocks.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
669
+ "vision_model.vision_tower.blocks.1.norm1.bias": "pytorch_model-00001-of-00002.bin",
670
+ "vision_model.vision_tower.blocks.1.norm1.weight": "pytorch_model-00001-of-00002.bin",
671
+ "vision_model.vision_tower.blocks.1.norm2.bias": "pytorch_model-00001-of-00002.bin",
672
+ "vision_model.vision_tower.blocks.1.norm2.weight": "pytorch_model-00001-of-00002.bin",
673
+ "vision_model.vision_tower.blocks.10.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
674
+ "vision_model.vision_tower.blocks.10.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
675
+ "vision_model.vision_tower.blocks.10.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
676
+ "vision_model.vision_tower.blocks.10.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
677
+ "vision_model.vision_tower.blocks.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
678
+ "vision_model.vision_tower.blocks.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
679
+ "vision_model.vision_tower.blocks.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
680
+ "vision_model.vision_tower.blocks.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
681
+ "vision_model.vision_tower.blocks.10.norm1.bias": "pytorch_model-00001-of-00002.bin",
682
+ "vision_model.vision_tower.blocks.10.norm1.weight": "pytorch_model-00001-of-00002.bin",
683
+ "vision_model.vision_tower.blocks.10.norm2.bias": "pytorch_model-00001-of-00002.bin",
684
+ "vision_model.vision_tower.blocks.10.norm2.weight": "pytorch_model-00001-of-00002.bin",
685
+ "vision_model.vision_tower.blocks.11.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
686
+ "vision_model.vision_tower.blocks.11.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
687
+ "vision_model.vision_tower.blocks.11.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
688
+ "vision_model.vision_tower.blocks.11.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
689
+ "vision_model.vision_tower.blocks.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
690
+ "vision_model.vision_tower.blocks.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
691
+ "vision_model.vision_tower.blocks.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
692
+ "vision_model.vision_tower.blocks.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
693
+ "vision_model.vision_tower.blocks.11.norm1.bias": "pytorch_model-00001-of-00002.bin",
694
+ "vision_model.vision_tower.blocks.11.norm1.weight": "pytorch_model-00001-of-00002.bin",
695
+ "vision_model.vision_tower.blocks.11.norm2.bias": "pytorch_model-00001-of-00002.bin",
696
+ "vision_model.vision_tower.blocks.11.norm2.weight": "pytorch_model-00001-of-00002.bin",
697
+ "vision_model.vision_tower.blocks.12.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
698
+ "vision_model.vision_tower.blocks.12.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
699
+ "vision_model.vision_tower.blocks.12.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
700
+ "vision_model.vision_tower.blocks.12.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
701
+ "vision_model.vision_tower.blocks.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
702
+ "vision_model.vision_tower.blocks.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
703
+ "vision_model.vision_tower.blocks.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
704
+ "vision_model.vision_tower.blocks.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
705
+ "vision_model.vision_tower.blocks.12.norm1.bias": "pytorch_model-00001-of-00002.bin",
706
+ "vision_model.vision_tower.blocks.12.norm1.weight": "pytorch_model-00001-of-00002.bin",
707
+ "vision_model.vision_tower.blocks.12.norm2.bias": "pytorch_model-00001-of-00002.bin",
708
+ "vision_model.vision_tower.blocks.12.norm2.weight": "pytorch_model-00001-of-00002.bin",
709
+ "vision_model.vision_tower.blocks.13.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
710
+ "vision_model.vision_tower.blocks.13.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
711
+ "vision_model.vision_tower.blocks.13.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
712
+ "vision_model.vision_tower.blocks.13.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
713
+ "vision_model.vision_tower.blocks.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
714
+ "vision_model.vision_tower.blocks.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
715
+ "vision_model.vision_tower.blocks.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
716
+ "vision_model.vision_tower.blocks.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
717
+ "vision_model.vision_tower.blocks.13.norm1.bias": "pytorch_model-00001-of-00002.bin",
718
+ "vision_model.vision_tower.blocks.13.norm1.weight": "pytorch_model-00001-of-00002.bin",
719
+ "vision_model.vision_tower.blocks.13.norm2.bias": "pytorch_model-00001-of-00002.bin",
720
+ "vision_model.vision_tower.blocks.13.norm2.weight": "pytorch_model-00001-of-00002.bin",
721
+ "vision_model.vision_tower.blocks.14.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
722
+ "vision_model.vision_tower.blocks.14.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
723
+ "vision_model.vision_tower.blocks.14.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
724
+ "vision_model.vision_tower.blocks.14.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
725
+ "vision_model.vision_tower.blocks.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
726
+ "vision_model.vision_tower.blocks.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
727
+ "vision_model.vision_tower.blocks.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
728
+ "vision_model.vision_tower.blocks.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
729
+ "vision_model.vision_tower.blocks.14.norm1.bias": "pytorch_model-00001-of-00002.bin",
730
+ "vision_model.vision_tower.blocks.14.norm1.weight": "pytorch_model-00001-of-00002.bin",
731
+ "vision_model.vision_tower.blocks.14.norm2.bias": "pytorch_model-00001-of-00002.bin",
732
+ "vision_model.vision_tower.blocks.14.norm2.weight": "pytorch_model-00001-of-00002.bin",
733
+ "vision_model.vision_tower.blocks.15.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
734
+ "vision_model.vision_tower.blocks.15.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
735
+ "vision_model.vision_tower.blocks.15.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
736
+ "vision_model.vision_tower.blocks.15.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
737
+ "vision_model.vision_tower.blocks.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
738
+ "vision_model.vision_tower.blocks.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
739
+ "vision_model.vision_tower.blocks.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
740
+ "vision_model.vision_tower.blocks.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
741
+ "vision_model.vision_tower.blocks.15.norm1.bias": "pytorch_model-00001-of-00002.bin",
742
+ "vision_model.vision_tower.blocks.15.norm1.weight": "pytorch_model-00001-of-00002.bin",
743
+ "vision_model.vision_tower.blocks.15.norm2.bias": "pytorch_model-00001-of-00002.bin",
744
+ "vision_model.vision_tower.blocks.15.norm2.weight": "pytorch_model-00001-of-00002.bin",
745
+ "vision_model.vision_tower.blocks.16.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
746
+ "vision_model.vision_tower.blocks.16.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
747
+ "vision_model.vision_tower.blocks.16.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
748
+ "vision_model.vision_tower.blocks.16.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
749
+ "vision_model.vision_tower.blocks.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
750
+ "vision_model.vision_tower.blocks.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
751
+ "vision_model.vision_tower.blocks.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
752
+ "vision_model.vision_tower.blocks.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
753
+ "vision_model.vision_tower.blocks.16.norm1.bias": "pytorch_model-00001-of-00002.bin",
754
+ "vision_model.vision_tower.blocks.16.norm1.weight": "pytorch_model-00001-of-00002.bin",
755
+ "vision_model.vision_tower.blocks.16.norm2.bias": "pytorch_model-00001-of-00002.bin",
756
+ "vision_model.vision_tower.blocks.16.norm2.weight": "pytorch_model-00001-of-00002.bin",
757
+ "vision_model.vision_tower.blocks.17.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
758
+ "vision_model.vision_tower.blocks.17.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
759
+ "vision_model.vision_tower.blocks.17.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
760
+ "vision_model.vision_tower.blocks.17.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
761
+ "vision_model.vision_tower.blocks.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
762
+ "vision_model.vision_tower.blocks.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
763
+ "vision_model.vision_tower.blocks.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
764
+ "vision_model.vision_tower.blocks.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
765
+ "vision_model.vision_tower.blocks.17.norm1.bias": "pytorch_model-00001-of-00002.bin",
766
+ "vision_model.vision_tower.blocks.17.norm1.weight": "pytorch_model-00001-of-00002.bin",
767
+ "vision_model.vision_tower.blocks.17.norm2.bias": "pytorch_model-00001-of-00002.bin",
768
+ "vision_model.vision_tower.blocks.17.norm2.weight": "pytorch_model-00001-of-00002.bin",
769
+ "vision_model.vision_tower.blocks.18.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
770
+ "vision_model.vision_tower.blocks.18.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
771
+ "vision_model.vision_tower.blocks.18.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
772
+ "vision_model.vision_tower.blocks.18.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
773
+ "vision_model.vision_tower.blocks.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
774
+ "vision_model.vision_tower.blocks.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
775
+ "vision_model.vision_tower.blocks.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
776
+ "vision_model.vision_tower.blocks.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
777
+ "vision_model.vision_tower.blocks.18.norm1.bias": "pytorch_model-00001-of-00002.bin",
778
+ "vision_model.vision_tower.blocks.18.norm1.weight": "pytorch_model-00001-of-00002.bin",
779
+ "vision_model.vision_tower.blocks.18.norm2.bias": "pytorch_model-00001-of-00002.bin",
780
+ "vision_model.vision_tower.blocks.18.norm2.weight": "pytorch_model-00001-of-00002.bin",
781
+ "vision_model.vision_tower.blocks.19.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
782
+ "vision_model.vision_tower.blocks.19.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
783
+ "vision_model.vision_tower.blocks.19.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
784
+ "vision_model.vision_tower.blocks.19.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
785
+ "vision_model.vision_tower.blocks.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
786
+ "vision_model.vision_tower.blocks.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
787
+ "vision_model.vision_tower.blocks.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
788
+ "vision_model.vision_tower.blocks.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
789
+ "vision_model.vision_tower.blocks.19.norm1.bias": "pytorch_model-00001-of-00002.bin",
790
+ "vision_model.vision_tower.blocks.19.norm1.weight": "pytorch_model-00001-of-00002.bin",
791
+ "vision_model.vision_tower.blocks.19.norm2.bias": "pytorch_model-00001-of-00002.bin",
792
+ "vision_model.vision_tower.blocks.19.norm2.weight": "pytorch_model-00001-of-00002.bin",
793
+ "vision_model.vision_tower.blocks.2.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
794
+ "vision_model.vision_tower.blocks.2.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
795
+ "vision_model.vision_tower.blocks.2.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
796
+ "vision_model.vision_tower.blocks.2.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
797
+ "vision_model.vision_tower.blocks.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
798
+ "vision_model.vision_tower.blocks.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
799
+ "vision_model.vision_tower.blocks.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
800
+ "vision_model.vision_tower.blocks.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
801
+ "vision_model.vision_tower.blocks.2.norm1.bias": "pytorch_model-00001-of-00002.bin",
802
+ "vision_model.vision_tower.blocks.2.norm1.weight": "pytorch_model-00001-of-00002.bin",
803
+ "vision_model.vision_tower.blocks.2.norm2.bias": "pytorch_model-00001-of-00002.bin",
804
+ "vision_model.vision_tower.blocks.2.norm2.weight": "pytorch_model-00001-of-00002.bin",
805
+ "vision_model.vision_tower.blocks.20.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
806
+ "vision_model.vision_tower.blocks.20.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
807
+ "vision_model.vision_tower.blocks.20.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
808
+ "vision_model.vision_tower.blocks.20.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
809
+ "vision_model.vision_tower.blocks.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
810
+ "vision_model.vision_tower.blocks.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
811
+ "vision_model.vision_tower.blocks.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
812
+ "vision_model.vision_tower.blocks.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
813
+ "vision_model.vision_tower.blocks.20.norm1.bias": "pytorch_model-00001-of-00002.bin",
814
+ "vision_model.vision_tower.blocks.20.norm1.weight": "pytorch_model-00001-of-00002.bin",
815
+ "vision_model.vision_tower.blocks.20.norm2.bias": "pytorch_model-00001-of-00002.bin",
816
+ "vision_model.vision_tower.blocks.20.norm2.weight": "pytorch_model-00001-of-00002.bin",
817
+ "vision_model.vision_tower.blocks.21.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
818
+ "vision_model.vision_tower.blocks.21.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
819
+ "vision_model.vision_tower.blocks.21.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
820
+ "vision_model.vision_tower.blocks.21.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
821
+ "vision_model.vision_tower.blocks.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
822
+ "vision_model.vision_tower.blocks.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
823
+ "vision_model.vision_tower.blocks.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
824
+ "vision_model.vision_tower.blocks.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
825
+ "vision_model.vision_tower.blocks.21.norm1.bias": "pytorch_model-00001-of-00002.bin",
826
+ "vision_model.vision_tower.blocks.21.norm1.weight": "pytorch_model-00001-of-00002.bin",
827
+ "vision_model.vision_tower.blocks.21.norm2.bias": "pytorch_model-00001-of-00002.bin",
828
+ "vision_model.vision_tower.blocks.21.norm2.weight": "pytorch_model-00001-of-00002.bin",
829
+ "vision_model.vision_tower.blocks.22.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
830
+ "vision_model.vision_tower.blocks.22.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
831
+ "vision_model.vision_tower.blocks.22.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
832
+ "vision_model.vision_tower.blocks.22.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
833
+ "vision_model.vision_tower.blocks.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
834
+ "vision_model.vision_tower.blocks.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
835
+ "vision_model.vision_tower.blocks.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
836
+ "vision_model.vision_tower.blocks.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
837
+ "vision_model.vision_tower.blocks.22.norm1.bias": "pytorch_model-00001-of-00002.bin",
838
+ "vision_model.vision_tower.blocks.22.norm1.weight": "pytorch_model-00001-of-00002.bin",
839
+ "vision_model.vision_tower.blocks.22.norm2.bias": "pytorch_model-00001-of-00002.bin",
840
+ "vision_model.vision_tower.blocks.22.norm2.weight": "pytorch_model-00001-of-00002.bin",
841
+ "vision_model.vision_tower.blocks.23.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
842
+ "vision_model.vision_tower.blocks.23.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
843
+ "vision_model.vision_tower.blocks.23.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
844
+ "vision_model.vision_tower.blocks.23.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
845
+ "vision_model.vision_tower.blocks.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
846
+ "vision_model.vision_tower.blocks.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
847
+ "vision_model.vision_tower.blocks.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
848
+ "vision_model.vision_tower.blocks.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
849
+ "vision_model.vision_tower.blocks.23.norm1.bias": "pytorch_model-00001-of-00002.bin",
850
+ "vision_model.vision_tower.blocks.23.norm1.weight": "pytorch_model-00001-of-00002.bin",
851
+ "vision_model.vision_tower.blocks.23.norm2.bias": "pytorch_model-00001-of-00002.bin",
852
+ "vision_model.vision_tower.blocks.23.norm2.weight": "pytorch_model-00001-of-00002.bin",
853
+ "vision_model.vision_tower.blocks.3.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
854
+ "vision_model.vision_tower.blocks.3.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
855
+ "vision_model.vision_tower.blocks.3.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
856
+ "vision_model.vision_tower.blocks.3.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
857
+ "vision_model.vision_tower.blocks.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
858
+ "vision_model.vision_tower.blocks.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
859
+ "vision_model.vision_tower.blocks.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
860
+ "vision_model.vision_tower.blocks.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
861
+ "vision_model.vision_tower.blocks.3.norm1.bias": "pytorch_model-00001-of-00002.bin",
862
+ "vision_model.vision_tower.blocks.3.norm1.weight": "pytorch_model-00001-of-00002.bin",
863
+ "vision_model.vision_tower.blocks.3.norm2.bias": "pytorch_model-00001-of-00002.bin",
864
+ "vision_model.vision_tower.blocks.3.norm2.weight": "pytorch_model-00001-of-00002.bin",
865
+ "vision_model.vision_tower.blocks.4.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
866
+ "vision_model.vision_tower.blocks.4.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
867
+ "vision_model.vision_tower.blocks.4.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
868
+ "vision_model.vision_tower.blocks.4.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
869
+ "vision_model.vision_tower.blocks.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
870
+ "vision_model.vision_tower.blocks.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
871
+ "vision_model.vision_tower.blocks.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
872
+ "vision_model.vision_tower.blocks.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
873
+ "vision_model.vision_tower.blocks.4.norm1.bias": "pytorch_model-00001-of-00002.bin",
874
+ "vision_model.vision_tower.blocks.4.norm1.weight": "pytorch_model-00001-of-00002.bin",
875
+ "vision_model.vision_tower.blocks.4.norm2.bias": "pytorch_model-00001-of-00002.bin",
876
+ "vision_model.vision_tower.blocks.4.norm2.weight": "pytorch_model-00001-of-00002.bin",
877
+ "vision_model.vision_tower.blocks.5.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
878
+ "vision_model.vision_tower.blocks.5.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
879
+ "vision_model.vision_tower.blocks.5.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
880
+ "vision_model.vision_tower.blocks.5.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
881
+ "vision_model.vision_tower.blocks.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
882
+ "vision_model.vision_tower.blocks.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
883
+ "vision_model.vision_tower.blocks.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
884
+ "vision_model.vision_tower.blocks.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
885
+ "vision_model.vision_tower.blocks.5.norm1.bias": "pytorch_model-00001-of-00002.bin",
886
+ "vision_model.vision_tower.blocks.5.norm1.weight": "pytorch_model-00001-of-00002.bin",
887
+ "vision_model.vision_tower.blocks.5.norm2.bias": "pytorch_model-00001-of-00002.bin",
888
+ "vision_model.vision_tower.blocks.5.norm2.weight": "pytorch_model-00001-of-00002.bin",
889
+ "vision_model.vision_tower.blocks.6.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
890
+ "vision_model.vision_tower.blocks.6.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
891
+ "vision_model.vision_tower.blocks.6.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
892
+ "vision_model.vision_tower.blocks.6.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
893
+ "vision_model.vision_tower.blocks.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
894
+ "vision_model.vision_tower.blocks.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
895
+ "vision_model.vision_tower.blocks.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
896
+ "vision_model.vision_tower.blocks.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
897
+ "vision_model.vision_tower.blocks.6.norm1.bias": "pytorch_model-00001-of-00002.bin",
898
+ "vision_model.vision_tower.blocks.6.norm1.weight": "pytorch_model-00001-of-00002.bin",
899
+ "vision_model.vision_tower.blocks.6.norm2.bias": "pytorch_model-00001-of-00002.bin",
900
+ "vision_model.vision_tower.blocks.6.norm2.weight": "pytorch_model-00001-of-00002.bin",
901
+ "vision_model.vision_tower.blocks.7.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
902
+ "vision_model.vision_tower.blocks.7.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
903
+ "vision_model.vision_tower.blocks.7.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
904
+ "vision_model.vision_tower.blocks.7.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
905
+ "vision_model.vision_tower.blocks.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
906
+ "vision_model.vision_tower.blocks.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
907
+ "vision_model.vision_tower.blocks.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
908
+ "vision_model.vision_tower.blocks.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
909
+ "vision_model.vision_tower.blocks.7.norm1.bias": "pytorch_model-00001-of-00002.bin",
910
+ "vision_model.vision_tower.blocks.7.norm1.weight": "pytorch_model-00001-of-00002.bin",
911
+ "vision_model.vision_tower.blocks.7.norm2.bias": "pytorch_model-00001-of-00002.bin",
912
+ "vision_model.vision_tower.blocks.7.norm2.weight": "pytorch_model-00001-of-00002.bin",
913
+ "vision_model.vision_tower.blocks.8.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
914
+ "vision_model.vision_tower.blocks.8.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
915
+ "vision_model.vision_tower.blocks.8.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
916
+ "vision_model.vision_tower.blocks.8.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
917
+ "vision_model.vision_tower.blocks.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
918
+ "vision_model.vision_tower.blocks.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
919
+ "vision_model.vision_tower.blocks.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
920
+ "vision_model.vision_tower.blocks.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
921
+ "vision_model.vision_tower.blocks.8.norm1.bias": "pytorch_model-00001-of-00002.bin",
922
+ "vision_model.vision_tower.blocks.8.norm1.weight": "pytorch_model-00001-of-00002.bin",
923
+ "vision_model.vision_tower.blocks.8.norm2.bias": "pytorch_model-00001-of-00002.bin",
924
+ "vision_model.vision_tower.blocks.8.norm2.weight": "pytorch_model-00001-of-00002.bin",
925
+ "vision_model.vision_tower.blocks.9.attn.proj.bias": "pytorch_model-00001-of-00002.bin",
926
+ "vision_model.vision_tower.blocks.9.attn.proj.weight": "pytorch_model-00001-of-00002.bin",
927
+ "vision_model.vision_tower.blocks.9.attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
928
+ "vision_model.vision_tower.blocks.9.attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
929
+ "vision_model.vision_tower.blocks.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
930
+ "vision_model.vision_tower.blocks.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
931
+ "vision_model.vision_tower.blocks.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
932
+ "vision_model.vision_tower.blocks.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
933
+ "vision_model.vision_tower.blocks.9.norm1.bias": "pytorch_model-00001-of-00002.bin",
934
+ "vision_model.vision_tower.blocks.9.norm1.weight": "pytorch_model-00001-of-00002.bin",
935
+ "vision_model.vision_tower.blocks.9.norm2.bias": "pytorch_model-00001-of-00002.bin",
936
+ "vision_model.vision_tower.blocks.9.norm2.weight": "pytorch_model-00001-of-00002.bin",
937
+ "vision_model.vision_tower.norm.bias": "pytorch_model-00001-of-00002.bin",
938
+ "vision_model.vision_tower.norm.weight": "pytorch_model-00001-of-00002.bin",
939
+ "vision_model.vision_tower.patch_embed.proj.bias": "pytorch_model-00001-of-00002.bin",
940
+ "vision_model.vision_tower.patch_embed.proj.weight": "pytorch_model-00001-of-00002.bin",
941
+ "vision_model.vision_tower.pos_embed": "pytorch_model-00001-of-00002.bin"
942
+ }
943
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<image_placeholder>",
4
+ "<patch_placeholder>",
5
+ "<|ref|>",
6
+ "<|/ref|>",
7
+ "<|det|>",
8
+ "<|/det|>",
9
+ "<|grounding|>",
10
+ "<|User|>",
11
+ "<|Assistant|>"
12
+ ],
13
+ "bos_token": "<｜begin▁of▁sentence｜>",
14
+ "eos_token": "<｜end▁of▁sentence｜>",
15
+ "pad_token": "<｜▁pad▁｜>"
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<｜begin▁of▁sentence｜>",
3
+ "clean_up_tokenization_spaces": false,
4
+ "eos_token": "<｜end▁of▁sentence｜>",
5
+ "model_max_length": 16384,
6
+ "pad_token": null,
7
+ "tokenizer_class": "LlamaTokenizer",
8
+ "unk_token": null,
9
+ "use_default_system_prompt": true
10
+ }