Hugging Face's logo

turing-motors
/
heron-chat-git-ja-stablelm-base-7b-v1

Image-to-Text
Transformers
Safetensors
Japanese
git_japanese_stablelm_alpha
text-generation
heron
vision
image-captioning
VQA
custom_code
Model card Files Community
Inoichan commited on
Commit
0de4fa8
•
1 Parent(s): cd33296

Upload GitJapaneseStableLMAlphaForCausalLM

Browse files
Files changed (6) hide show
  1. config.json +45 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00003.safetensors +3 -0
  4. model-00002-of-00003.safetensors +3 -0
  5. model-00003-of-00003.safetensors +3 -0
  6. model.safetensors.index.json +662 -0
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "./checkpoints/heron_git_v1/checkpoint-4800/",
4
+ "architectures": [
5
+ "GitJapaneseStableLMAlphaForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "stabilityai/japanese-stablelm-base-alpha-7b--configuration_japanese_stablelm_alpha.JapaneseStableLMAlphaConfig",
9
+ "AutoModelForCausalLM": "stabilityai/japanese-stablelm-base-alpha-7b--modeling_japanese_stablelm_alpha.JapaneseStableLMAlphaForCausalLM"
10
+ },
11
+ "bos_token_id": 3,
12
+ "classifier_dropout": 0.1,
13
+ "eos_token_id": 3,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "layer_norm_eps": 1e-05,
18
+ "max_position_embeddings": 2048,
19
+ "model_type": "git_japanese_stablelm_alpha",
20
+ "num_attention_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_image_with_embedding": null,
23
+ "rotary_emb_base": 10000,
24
+ "rotary_pct": 0.25,
25
+ "rotary_scale_base": 512,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.30.2",
29
+ "use_bias_in_mlp": false,
30
+ "use_cache": true,
31
+ "use_parallel_residual": true,
32
+ "vision_config": {
33
+ "dropout": 0.0,
34
+ "hidden_size": 1024,
35
+ "image_size": 336,
36
+ "intermediate_size": 4096,
37
+ "model_type": "clip_vision_model",
38
+ "num_attention_heads": 16,
39
+ "num_hidden_layers": 24,
40
+ "patch_size": 14,
41
+ "projection_dim": 768
42
+ },
43
+ "vision_model_name": "openai/clip-vit-large-patch14-336",
44
+ "vocab_size": 65536
45
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 3,
4
+ "eos_token_id": 3,
5
+ "transformers_version": "4.37.2"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d080d2e59a61069590db3080adf9fae7875809d7c428a59be3253a004a905a48
3
+ size 4989333464
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c0b6c6b8b9e91a86d23ce978288a9ceeff74be3ae8bd2995bc3b6c435008ef
3
+ size 4991431328
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aadece306f68220b62adbe7900353b940b760aaa894e8a4c1ae22aa178ff3242
3
+ size 4661049392
model.safetensors.index.json ADDED
@@ -0,0 +1,662 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14641723392
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00003-of-00003.safetensors",
7
+ "transformer.embed_in.weight": "model-00001-of-00003.safetensors",
8
+ "transformer.final_layer_norm.bias": "model-00003-of-00003.safetensors",
9
+ "transformer.final_layer_norm.weight": "model-00003-of-00003.safetensors",
10
+ "transformer.image_encoder.vision_model.embeddings.class_embedding": "model-00003-of-00003.safetensors",
11
+ "transformer.image_encoder.vision_model.embeddings.patch_embedding.weight": "model-00003-of-00003.safetensors",
12
+ "transformer.image_encoder.vision_model.embeddings.position_embedding.weight": "model-00003-of-00003.safetensors",
13
+ "transformer.image_encoder.vision_model.encoder.layers.0.layer_norm1.bias": "model-00003-of-00003.safetensors",
14
+ "transformer.image_encoder.vision_model.encoder.layers.0.layer_norm1.weight": "model-00003-of-00003.safetensors",
15
+ "transformer.image_encoder.vision_model.encoder.layers.0.layer_norm2.bias": "model-00003-of-00003.safetensors",
16
+ "transformer.image_encoder.vision_model.encoder.layers.0.layer_norm2.weight": "model-00003-of-00003.safetensors",
17
+ "transformer.image_encoder.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00003-of-00003.safetensors",
18
+ "transformer.image_encoder.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00003-of-00003.safetensors",
19
+ "transformer.image_encoder.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00003-of-00003.safetensors",
20
+ "transformer.image_encoder.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00003-of-00003.safetensors",
21
+ "transformer.image_encoder.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
22
+ "transformer.image_encoder.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
23
+ "transformer.image_encoder.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
24
+ "transformer.image_encoder.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
25
+ "transformer.image_encoder.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
26
+ "transformer.image_encoder.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
27
+ "transformer.image_encoder.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
28
+ "transformer.image_encoder.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
29
+ "transformer.image_encoder.vision_model.encoder.layers.1.layer_norm1.bias": "model-00003-of-00003.safetensors",
30
+ "transformer.image_encoder.vision_model.encoder.layers.1.layer_norm1.weight": "model-00003-of-00003.safetensors",
31
+ "transformer.image_encoder.vision_model.encoder.layers.1.layer_norm2.bias": "model-00003-of-00003.safetensors",
32
+ "transformer.image_encoder.vision_model.encoder.layers.1.layer_norm2.weight": "model-00003-of-00003.safetensors",
33
+ "transformer.image_encoder.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00003-of-00003.safetensors",
34
+ "transformer.image_encoder.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00003-of-00003.safetensors",
35
+ "transformer.image_encoder.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00003-of-00003.safetensors",
36
+ "transformer.image_encoder.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00003-of-00003.safetensors",
37
+ "transformer.image_encoder.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
38
+ "transformer.image_encoder.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
39
+ "transformer.image_encoder.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
40
+ "transformer.image_encoder.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
41
+ "transformer.image_encoder.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
42
+ "transformer.image_encoder.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
43
+ "transformer.image_encoder.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
44
+ "transformer.image_encoder.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
45
+ "transformer.image_encoder.vision_model.encoder.layers.10.layer_norm1.bias": "model-00003-of-00003.safetensors",
46
+ "transformer.image_encoder.vision_model.encoder.layers.10.layer_norm1.weight": "model-00003-of-00003.safetensors",
47
+ "transformer.image_encoder.vision_model.encoder.layers.10.layer_norm2.bias": "model-00003-of-00003.safetensors",
48
+ "transformer.image_encoder.vision_model.encoder.layers.10.layer_norm2.weight": "model-00003-of-00003.safetensors",
49
+ "transformer.image_encoder.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00003-of-00003.safetensors",
50
+ "transformer.image_encoder.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00003-of-00003.safetensors",
51
+ "transformer.image_encoder.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00003-of-00003.safetensors",
52
+ "transformer.image_encoder.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00003-of-00003.safetensors",
53
+ "transformer.image_encoder.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
54
+ "transformer.image_encoder.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
55
+ "transformer.image_encoder.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
56
+ "transformer.image_encoder.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
57
+ "transformer.image_encoder.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
58
+ "transformer.image_encoder.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
59
+ "transformer.image_encoder.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
60
+ "transformer.image_encoder.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
61
+ "transformer.image_encoder.vision_model.encoder.layers.11.layer_norm1.bias": "model-00003-of-00003.safetensors",
62
+ "transformer.image_encoder.vision_model.encoder.layers.11.layer_norm1.weight": "model-00003-of-00003.safetensors",
63
+ "transformer.image_encoder.vision_model.encoder.layers.11.layer_norm2.bias": "model-00003-of-00003.safetensors",
64
+ "transformer.image_encoder.vision_model.encoder.layers.11.layer_norm2.weight": "model-00003-of-00003.safetensors",
65
+ "transformer.image_encoder.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00003-of-00003.safetensors",
66
+ "transformer.image_encoder.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00003-of-00003.safetensors",
67
+ "transformer.image_encoder.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00003-of-00003.safetensors",
68
+ "transformer.image_encoder.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00003-of-00003.safetensors",
69
+ "transformer.image_encoder.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
70
+ "transformer.image_encoder.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
71
+ "transformer.image_encoder.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
72
+ "transformer.image_encoder.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
73
+ "transformer.image_encoder.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
74
+ "transformer.image_encoder.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
75
+ "transformer.image_encoder.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
76
+ "transformer.image_encoder.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
77
+ "transformer.image_encoder.vision_model.encoder.layers.12.layer_norm1.bias": "model-00003-of-00003.safetensors",
78
+ "transformer.image_encoder.vision_model.encoder.layers.12.layer_norm1.weight": "model-00003-of-00003.safetensors",
79
+ "transformer.image_encoder.vision_model.encoder.layers.12.layer_norm2.bias": "model-00003-of-00003.safetensors",
80
+ "transformer.image_encoder.vision_model.encoder.layers.12.layer_norm2.weight": "model-00003-of-00003.safetensors",
81
+ "transformer.image_encoder.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00003-of-00003.safetensors",
82
+ "transformer.image_encoder.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00003-of-00003.safetensors",
83
+ "transformer.image_encoder.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00003-of-00003.safetensors",
84
+ "transformer.image_encoder.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00003-of-00003.safetensors",
85
+ "transformer.image_encoder.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
86
+ "transformer.image_encoder.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
87
+ "transformer.image_encoder.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
88
+ "transformer.image_encoder.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
89
+ "transformer.image_encoder.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
90
+ "transformer.image_encoder.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
91
+ "transformer.image_encoder.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
92
+ "transformer.image_encoder.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
93
+ "transformer.image_encoder.vision_model.encoder.layers.13.layer_norm1.bias": "model-00003-of-00003.safetensors",
94
+ "transformer.image_encoder.vision_model.encoder.layers.13.layer_norm1.weight": "model-00003-of-00003.safetensors",
95
+ "transformer.image_encoder.vision_model.encoder.layers.13.layer_norm2.bias": "model-00003-of-00003.safetensors",
96
+ "transformer.image_encoder.vision_model.encoder.layers.13.layer_norm2.weight": "model-00003-of-00003.safetensors",
97
+ "transformer.image_encoder.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00003-of-00003.safetensors",
98
+ "transformer.image_encoder.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00003-of-00003.safetensors",
99
+ "transformer.image_encoder.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00003-of-00003.safetensors",
100
+ "transformer.image_encoder.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00003-of-00003.safetensors",
101
+ "transformer.image_encoder.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
102
+ "transformer.image_encoder.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
103
+ "transformer.image_encoder.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
104
+ "transformer.image_encoder.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
105
+ "transformer.image_encoder.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
106
+ "transformer.image_encoder.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
107
+ "transformer.image_encoder.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
108
+ "transformer.image_encoder.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
109
+ "transformer.image_encoder.vision_model.encoder.layers.14.layer_norm1.bias": "model-00003-of-00003.safetensors",
110
+ "transformer.image_encoder.vision_model.encoder.layers.14.layer_norm1.weight": "model-00003-of-00003.safetensors",
111
+ "transformer.image_encoder.vision_model.encoder.layers.14.layer_norm2.bias": "model-00003-of-00003.safetensors",
112
+ "transformer.image_encoder.vision_model.encoder.layers.14.layer_norm2.weight": "model-00003-of-00003.safetensors",
113
+ "transformer.image_encoder.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00003-of-00003.safetensors",
114
+ "transformer.image_encoder.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00003-of-00003.safetensors",
115
+ "transformer.image_encoder.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00003-of-00003.safetensors",
116
+ "transformer.image_encoder.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00003-of-00003.safetensors",
117
+ "transformer.image_encoder.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
118
+ "transformer.image_encoder.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
119
+ "transformer.image_encoder.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
120
+ "transformer.image_encoder.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
121
+ "transformer.image_encoder.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
122
+ "transformer.image_encoder.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
123
+ "transformer.image_encoder.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
124
+ "transformer.image_encoder.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
125
+ "transformer.image_encoder.vision_model.encoder.layers.15.layer_norm1.bias": "model-00003-of-00003.safetensors",
126
+ "transformer.image_encoder.vision_model.encoder.layers.15.layer_norm1.weight": "model-00003-of-00003.safetensors",
127
+ "transformer.image_encoder.vision_model.encoder.layers.15.layer_norm2.bias": "model-00003-of-00003.safetensors",
128
+ "transformer.image_encoder.vision_model.encoder.layers.15.layer_norm2.weight": "model-00003-of-00003.safetensors",
129
+ "transformer.image_encoder.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00003-of-00003.safetensors",
130
+ "transformer.image_encoder.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00003-of-00003.safetensors",
131
+ "transformer.image_encoder.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00003-of-00003.safetensors",
132
+ "transformer.image_encoder.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00003-of-00003.safetensors",
133
+ "transformer.image_encoder.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
134
+ "transformer.image_encoder.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
135
+ "transformer.image_encoder.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
136
+ "transformer.image_encoder.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
137
+ "transformer.image_encoder.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
138
+ "transformer.image_encoder.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
139
+ "transformer.image_encoder.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
140
+ "transformer.image_encoder.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
141
+ "transformer.image_encoder.vision_model.encoder.layers.16.layer_norm1.bias": "model-00003-of-00003.safetensors",
142
+ "transformer.image_encoder.vision_model.encoder.layers.16.layer_norm1.weight": "model-00003-of-00003.safetensors",
143
+ "transformer.image_encoder.vision_model.encoder.layers.16.layer_norm2.bias": "model-00003-of-00003.safetensors",
144
+ "transformer.image_encoder.vision_model.encoder.layers.16.layer_norm2.weight": "model-00003-of-00003.safetensors",
145
+ "transformer.image_encoder.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00003-of-00003.safetensors",
146
+ "transformer.image_encoder.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00003-of-00003.safetensors",
147
+ "transformer.image_encoder.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00003-of-00003.safetensors",
148
+ "transformer.image_encoder.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00003-of-00003.safetensors",
149
+ "transformer.image_encoder.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
150
+ "transformer.image_encoder.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
151
+ "transformer.image_encoder.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
152
+ "transformer.image_encoder.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
153
+ "transformer.image_encoder.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
154
+ "transformer.image_encoder.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
155
+ "transformer.image_encoder.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
156
+ "transformer.image_encoder.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
157
+ "transformer.image_encoder.vision_model.encoder.layers.17.layer_norm1.bias": "model-00003-of-00003.safetensors",
158
+ "transformer.image_encoder.vision_model.encoder.layers.17.layer_norm1.weight": "model-00003-of-00003.safetensors",
159
+ "transformer.image_encoder.vision_model.encoder.layers.17.layer_norm2.bias": "model-00003-of-00003.safetensors",
160
+ "transformer.image_encoder.vision_model.encoder.layers.17.layer_norm2.weight": "model-00003-of-00003.safetensors",
161
+ "transformer.image_encoder.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00003-of-00003.safetensors",
162
+ "transformer.image_encoder.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00003-of-00003.safetensors",
163
+ "transformer.image_encoder.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00003-of-00003.safetensors",
164
+ "transformer.image_encoder.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00003-of-00003.safetensors",
165
+ "transformer.image_encoder.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
166
+ "transformer.image_encoder.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "transformer.image_encoder.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
168
+ "transformer.image_encoder.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
169
+ "transformer.image_encoder.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
170
+ "transformer.image_encoder.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
171
+ "transformer.image_encoder.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
172
+ "transformer.image_encoder.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
173
+ "transformer.image_encoder.vision_model.encoder.layers.18.layer_norm1.bias": "model-00003-of-00003.safetensors",
174
+ "transformer.image_encoder.vision_model.encoder.layers.18.layer_norm1.weight": "model-00003-of-00003.safetensors",
175
+ "transformer.image_encoder.vision_model.encoder.layers.18.layer_norm2.bias": "model-00003-of-00003.safetensors",
176
+ "transformer.image_encoder.vision_model.encoder.layers.18.layer_norm2.weight": "model-00003-of-00003.safetensors",
177
+ "transformer.image_encoder.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00003-of-00003.safetensors",
178
+ "transformer.image_encoder.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00003-of-00003.safetensors",
179
+ "transformer.image_encoder.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00003-of-00003.safetensors",
180
+ "transformer.image_encoder.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00003-of-00003.safetensors",
181
+ "transformer.image_encoder.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
182
+ "transformer.image_encoder.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
183
+ "transformer.image_encoder.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
184
+ "transformer.image_encoder.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
185
+ "transformer.image_encoder.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
186
+ "transformer.image_encoder.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "transformer.image_encoder.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
188
+ "transformer.image_encoder.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
189
+ "transformer.image_encoder.vision_model.encoder.layers.19.layer_norm1.bias": "model-00003-of-00003.safetensors",
190
+ "transformer.image_encoder.vision_model.encoder.layers.19.layer_norm1.weight": "model-00003-of-00003.safetensors",
191
+ "transformer.image_encoder.vision_model.encoder.layers.19.layer_norm2.bias": "model-00003-of-00003.safetensors",
192
+ "transformer.image_encoder.vision_model.encoder.layers.19.layer_norm2.weight": "model-00003-of-00003.safetensors",
193
+ "transformer.image_encoder.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00003-of-00003.safetensors",
194
+ "transformer.image_encoder.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00003-of-00003.safetensors",
195
+ "transformer.image_encoder.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00003-of-00003.safetensors",
196
+ "transformer.image_encoder.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00003-of-00003.safetensors",
197
+ "transformer.image_encoder.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
198
+ "transformer.image_encoder.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
199
+ "transformer.image_encoder.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
200
+ "transformer.image_encoder.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
201
+ "transformer.image_encoder.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
202
+ "transformer.image_encoder.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
203
+ "transformer.image_encoder.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
204
+ "transformer.image_encoder.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
205
+ "transformer.image_encoder.vision_model.encoder.layers.2.layer_norm1.bias": "model-00003-of-00003.safetensors",
206
+ "transformer.image_encoder.vision_model.encoder.layers.2.layer_norm1.weight": "model-00003-of-00003.safetensors",
207
+ "transformer.image_encoder.vision_model.encoder.layers.2.layer_norm2.bias": "model-00003-of-00003.safetensors",
208
+ "transformer.image_encoder.vision_model.encoder.layers.2.layer_norm2.weight": "model-00003-of-00003.safetensors",
209
+ "transformer.image_encoder.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00003-of-00003.safetensors",
210
+ "transformer.image_encoder.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00003-of-00003.safetensors",
211
+ "transformer.image_encoder.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00003-of-00003.safetensors",
212
+ "transformer.image_encoder.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00003-of-00003.safetensors",
213
+ "transformer.image_encoder.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
214
+ "transformer.image_encoder.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
215
+ "transformer.image_encoder.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
216
+ "transformer.image_encoder.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
217
+ "transformer.image_encoder.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
218
+ "transformer.image_encoder.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
219
+ "transformer.image_encoder.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
220
+ "transformer.image_encoder.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
221
+ "transformer.image_encoder.vision_model.encoder.layers.20.layer_norm1.bias": "model-00003-of-00003.safetensors",
222
+ "transformer.image_encoder.vision_model.encoder.layers.20.layer_norm1.weight": "model-00003-of-00003.safetensors",
223
+ "transformer.image_encoder.vision_model.encoder.layers.20.layer_norm2.bias": "model-00003-of-00003.safetensors",
224
+ "transformer.image_encoder.vision_model.encoder.layers.20.layer_norm2.weight": "model-00003-of-00003.safetensors",
225
+ "transformer.image_encoder.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00003-of-00003.safetensors",
226
+ "transformer.image_encoder.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00003-of-00003.safetensors",
227
+ "transformer.image_encoder.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00003-of-00003.safetensors",
228
+ "transformer.image_encoder.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00003-of-00003.safetensors",
229
+ "transformer.image_encoder.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
230
+ "transformer.image_encoder.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
231
+ "transformer.image_encoder.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
232
+ "transformer.image_encoder.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
233
+ "transformer.image_encoder.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
234
+ "transformer.image_encoder.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
235
+ "transformer.image_encoder.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
236
+ "transformer.image_encoder.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
237
+ "transformer.image_encoder.vision_model.encoder.layers.21.layer_norm1.bias": "model-00003-of-00003.safetensors",
238
+ "transformer.image_encoder.vision_model.encoder.layers.21.layer_norm1.weight": "model-00003-of-00003.safetensors",
239
+ "transformer.image_encoder.vision_model.encoder.layers.21.layer_norm2.bias": "model-00003-of-00003.safetensors",
240
+ "transformer.image_encoder.vision_model.encoder.layers.21.layer_norm2.weight": "model-00003-of-00003.safetensors",
241
+ "transformer.image_encoder.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00003-of-00003.safetensors",
242
+ "transformer.image_encoder.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00003-of-00003.safetensors",
243
+ "transformer.image_encoder.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00003-of-00003.safetensors",
244
+ "transformer.image_encoder.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00003-of-00003.safetensors",
245
+ "transformer.image_encoder.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
246
+ "transformer.image_encoder.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
247
+ "transformer.image_encoder.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
248
+ "transformer.image_encoder.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
249
+ "transformer.image_encoder.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
250
+ "transformer.image_encoder.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
251
+ "transformer.image_encoder.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
252
+ "transformer.image_encoder.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
253
+ "transformer.image_encoder.vision_model.encoder.layers.22.layer_norm1.bias": "model-00003-of-00003.safetensors",
254
+ "transformer.image_encoder.vision_model.encoder.layers.22.layer_norm1.weight": "model-00003-of-00003.safetensors",
255
+ "transformer.image_encoder.vision_model.encoder.layers.22.layer_norm2.bias": "model-00003-of-00003.safetensors",
256
+ "transformer.image_encoder.vision_model.encoder.layers.22.layer_norm2.weight": "model-00003-of-00003.safetensors",
257
+ "transformer.image_encoder.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00003-of-00003.safetensors",
258
+ "transformer.image_encoder.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00003-of-00003.safetensors",
259
+ "transformer.image_encoder.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00003-of-00003.safetensors",
260
+ "transformer.image_encoder.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00003-of-00003.safetensors",
261
+ "transformer.image_encoder.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
262
+ "transformer.image_encoder.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
263
+ "transformer.image_encoder.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
264
+ "transformer.image_encoder.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
265
+ "transformer.image_encoder.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
266
+ "transformer.image_encoder.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
267
+ "transformer.image_encoder.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
268
+ "transformer.image_encoder.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
269
+ "transformer.image_encoder.vision_model.encoder.layers.23.layer_norm1.bias": "model-00003-of-00003.safetensors",
270
+ "transformer.image_encoder.vision_model.encoder.layers.23.layer_norm1.weight": "model-00003-of-00003.safetensors",
271
+ "transformer.image_encoder.vision_model.encoder.layers.23.layer_norm2.bias": "model-00003-of-00003.safetensors",
272
+ "transformer.image_encoder.vision_model.encoder.layers.23.layer_norm2.weight": "model-00003-of-00003.safetensors",
273
+ "transformer.image_encoder.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00003-of-00003.safetensors",
274
+ "transformer.image_encoder.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00003-of-00003.safetensors",
275
+ "transformer.image_encoder.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00003-of-00003.safetensors",
276
+ "transformer.image_encoder.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00003-of-00003.safetensors",
277
+ "transformer.image_encoder.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
278
+ "transformer.image_encoder.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
279
+ "transformer.image_encoder.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
280
+ "transformer.image_encoder.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
281
+ "transformer.image_encoder.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
282
+ "transformer.image_encoder.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
283
+ "transformer.image_encoder.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
284
+ "transformer.image_encoder.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
285
+ "transformer.image_encoder.vision_model.encoder.layers.3.layer_norm1.bias": "model-00003-of-00003.safetensors",
286
+ "transformer.image_encoder.vision_model.encoder.layers.3.layer_norm1.weight": "model-00003-of-00003.safetensors",
287
+ "transformer.image_encoder.vision_model.encoder.layers.3.layer_norm2.bias": "model-00003-of-00003.safetensors",
288
+ "transformer.image_encoder.vision_model.encoder.layers.3.layer_norm2.weight": "model-00003-of-00003.safetensors",
289
+ "transformer.image_encoder.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00003-of-00003.safetensors",
290
+ "transformer.image_encoder.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00003-of-00003.safetensors",
291
+ "transformer.image_encoder.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00003-of-00003.safetensors",
292
+ "transformer.image_encoder.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00003-of-00003.safetensors",
293
+ "transformer.image_encoder.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
294
+ "transformer.image_encoder.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
295
+ "transformer.image_encoder.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
296
+ "transformer.image_encoder.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
297
+ "transformer.image_encoder.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
298
+ "transformer.image_encoder.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
299
+ "transformer.image_encoder.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
300
+ "transformer.image_encoder.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
301
+ "transformer.image_encoder.vision_model.encoder.layers.4.layer_norm1.bias": "model-00003-of-00003.safetensors",
302
+ "transformer.image_encoder.vision_model.encoder.layers.4.layer_norm1.weight": "model-00003-of-00003.safetensors",
303
+ "transformer.image_encoder.vision_model.encoder.layers.4.layer_norm2.bias": "model-00003-of-00003.safetensors",
304
+ "transformer.image_encoder.vision_model.encoder.layers.4.layer_norm2.weight": "model-00003-of-00003.safetensors",
305
+ "transformer.image_encoder.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00003-of-00003.safetensors",
306
+ "transformer.image_encoder.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00003-of-00003.safetensors",
307
+ "transformer.image_encoder.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00003-of-00003.safetensors",
308
+ "transformer.image_encoder.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00003-of-00003.safetensors",
309
+ "transformer.image_encoder.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
310
+ "transformer.image_encoder.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
311
+ "transformer.image_encoder.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
312
+ "transformer.image_encoder.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
313
+ "transformer.image_encoder.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
314
+ "transformer.image_encoder.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
315
+ "transformer.image_encoder.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
316
+ "transformer.image_encoder.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
317
+ "transformer.image_encoder.vision_model.encoder.layers.5.layer_norm1.bias": "model-00003-of-00003.safetensors",
318
+ "transformer.image_encoder.vision_model.encoder.layers.5.layer_norm1.weight": "model-00003-of-00003.safetensors",
319
+ "transformer.image_encoder.vision_model.encoder.layers.5.layer_norm2.bias": "model-00003-of-00003.safetensors",
320
+ "transformer.image_encoder.vision_model.encoder.layers.5.layer_norm2.weight": "model-00003-of-00003.safetensors",
321
+ "transformer.image_encoder.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00003-of-00003.safetensors",
322
+ "transformer.image_encoder.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00003-of-00003.safetensors",
323
+ "transformer.image_encoder.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00003-of-00003.safetensors",
324
+ "transformer.image_encoder.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00003-of-00003.safetensors",
325
+ "transformer.image_encoder.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
326
+ "transformer.image_encoder.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
327
+ "transformer.image_encoder.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
328
+ "transformer.image_encoder.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
329
+ "transformer.image_encoder.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
330
+ "transformer.image_encoder.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
331
+ "transformer.image_encoder.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
332
+ "transformer.image_encoder.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
333
+ "transformer.image_encoder.vision_model.encoder.layers.6.layer_norm1.bias": "model-00003-of-00003.safetensors",
334
+ "transformer.image_encoder.vision_model.encoder.layers.6.layer_norm1.weight": "model-00003-of-00003.safetensors",
335
+ "transformer.image_encoder.vision_model.encoder.layers.6.layer_norm2.bias": "model-00003-of-00003.safetensors",
336
+ "transformer.image_encoder.vision_model.encoder.layers.6.layer_norm2.weight": "model-00003-of-00003.safetensors",
337
+ "transformer.image_encoder.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00003-of-00003.safetensors",
338
+ "transformer.image_encoder.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00003-of-00003.safetensors",
339
+ "transformer.image_encoder.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00003-of-00003.safetensors",
340
+ "transformer.image_encoder.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00003-of-00003.safetensors",
341
+ "transformer.image_encoder.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
342
+ "transformer.image_encoder.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
343
+ "transformer.image_encoder.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
344
+ "transformer.image_encoder.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
345
+ "transformer.image_encoder.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
346
+ "transformer.image_encoder.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
347
+ "transformer.image_encoder.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
348
+ "transformer.image_encoder.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
349
+ "transformer.image_encoder.vision_model.encoder.layers.7.layer_norm1.bias": "model-00003-of-00003.safetensors",
350
+ "transformer.image_encoder.vision_model.encoder.layers.7.layer_norm1.weight": "model-00003-of-00003.safetensors",
351
+ "transformer.image_encoder.vision_model.encoder.layers.7.layer_norm2.bias": "model-00003-of-00003.safetensors",
352
+ "transformer.image_encoder.vision_model.encoder.layers.7.layer_norm2.weight": "model-00003-of-00003.safetensors",
353
+ "transformer.image_encoder.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00003-of-00003.safetensors",
354
+ "transformer.image_encoder.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00003-of-00003.safetensors",
355
+ "transformer.image_encoder.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00003-of-00003.safetensors",
356
+ "transformer.image_encoder.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00003-of-00003.safetensors",
357
+ "transformer.image_encoder.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
358
+ "transformer.image_encoder.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
359
+ "transformer.image_encoder.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
360
+ "transformer.image_encoder.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
361
+ "transformer.image_encoder.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
362
+ "transformer.image_encoder.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
363
+ "transformer.image_encoder.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
364
+ "transformer.image_encoder.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
365
+ "transformer.image_encoder.vision_model.encoder.layers.8.layer_norm1.bias": "model-00003-of-00003.safetensors",
366
+ "transformer.image_encoder.vision_model.encoder.layers.8.layer_norm1.weight": "model-00003-of-00003.safetensors",
367
+ "transformer.image_encoder.vision_model.encoder.layers.8.layer_norm2.bias": "model-00003-of-00003.safetensors",
368
+ "transformer.image_encoder.vision_model.encoder.layers.8.layer_norm2.weight": "model-00003-of-00003.safetensors",
369
+ "transformer.image_encoder.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00003-of-00003.safetensors",
370
+ "transformer.image_encoder.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00003-of-00003.safetensors",
371
+ "transformer.image_encoder.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00003-of-00003.safetensors",
372
+ "transformer.image_encoder.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00003-of-00003.safetensors",
373
+ "transformer.image_encoder.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
374
+ "transformer.image_encoder.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
375
+ "transformer.image_encoder.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
376
+ "transformer.image_encoder.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
377
+ "transformer.image_encoder.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
378
+ "transformer.image_encoder.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
379
+ "transformer.image_encoder.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
380
+ "transformer.image_encoder.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
381
+ "transformer.image_encoder.vision_model.encoder.layers.9.layer_norm1.bias": "model-00003-of-00003.safetensors",
382
+ "transformer.image_encoder.vision_model.encoder.layers.9.layer_norm1.weight": "model-00003-of-00003.safetensors",
383
+ "transformer.image_encoder.vision_model.encoder.layers.9.layer_norm2.bias": "model-00003-of-00003.safetensors",
384
+ "transformer.image_encoder.vision_model.encoder.layers.9.layer_norm2.weight": "model-00003-of-00003.safetensors",
385
+ "transformer.image_encoder.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00003-of-00003.safetensors",
386
+ "transformer.image_encoder.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00003-of-00003.safetensors",
387
+ "transformer.image_encoder.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00003-of-00003.safetensors",
388
+ "transformer.image_encoder.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00003-of-00003.safetensors",
389
+ "transformer.image_encoder.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
390
+ "transformer.image_encoder.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
391
+ "transformer.image_encoder.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
392
+ "transformer.image_encoder.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
393
+ "transformer.image_encoder.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
394
+ "transformer.image_encoder.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
395
+ "transformer.image_encoder.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
396
+ "transformer.image_encoder.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
397
+ "transformer.image_encoder.vision_model.post_layernorm.bias": "model-00003-of-00003.safetensors",
398
+ "transformer.image_encoder.vision_model.post_layernorm.weight": "model-00003-of-00003.safetensors",
399
+ "transformer.image_encoder.vision_model.pre_layrnorm.bias": "model-00003-of-00003.safetensors",
400
+ "transformer.image_encoder.vision_model.pre_layrnorm.weight": "model-00003-of-00003.safetensors",
401
+ "transformer.layers.0.attention.dense.weight": "model-00001-of-00003.safetensors",
402
+ "transformer.layers.0.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
403
+ "transformer.layers.0.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
404
+ "transformer.layers.0.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
405
+ "transformer.layers.0.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
406
+ "transformer.layers.0.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
407
+ "transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
408
+ "transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
409
+ "transformer.layers.1.attention.dense.weight": "model-00001-of-00003.safetensors",
410
+ "transformer.layers.1.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
411
+ "transformer.layers.1.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
412
+ "transformer.layers.1.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
413
+ "transformer.layers.1.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
414
+ "transformer.layers.1.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
415
+ "transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
416
+ "transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
417
+ "transformer.layers.10.attention.dense.weight": "model-00001-of-00003.safetensors",
418
+ "transformer.layers.10.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
419
+ "transformer.layers.10.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
420
+ "transformer.layers.10.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
421
+ "transformer.layers.10.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
422
+ "transformer.layers.10.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
423
+ "transformer.layers.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
424
+ "transformer.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
425
+ "transformer.layers.11.attention.dense.weight": "model-00002-of-00003.safetensors",
426
+ "transformer.layers.11.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
427
+ "transformer.layers.11.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
428
+ "transformer.layers.11.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
429
+ "transformer.layers.11.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
430
+ "transformer.layers.11.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
431
+ "transformer.layers.11.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
432
+ "transformer.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
433
+ "transformer.layers.12.attention.dense.weight": "model-00002-of-00003.safetensors",
434
+ "transformer.layers.12.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
435
+ "transformer.layers.12.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
436
+ "transformer.layers.12.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
437
+ "transformer.layers.12.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
438
+ "transformer.layers.12.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
439
+ "transformer.layers.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
440
+ "transformer.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
441
+ "transformer.layers.13.attention.dense.weight": "model-00002-of-00003.safetensors",
442
+ "transformer.layers.13.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
443
+ "transformer.layers.13.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
444
+ "transformer.layers.13.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
445
+ "transformer.layers.13.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
446
+ "transformer.layers.13.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
447
+ "transformer.layers.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
448
+ "transformer.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
449
+ "transformer.layers.14.attention.dense.weight": "model-00002-of-00003.safetensors",
450
+ "transformer.layers.14.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
451
+ "transformer.layers.14.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
452
+ "transformer.layers.14.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
453
+ "transformer.layers.14.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
454
+ "transformer.layers.14.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
455
+ "transformer.layers.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
456
+ "transformer.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
457
+ "transformer.layers.15.attention.dense.weight": "model-00002-of-00003.safetensors",
458
+ "transformer.layers.15.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
459
+ "transformer.layers.15.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
460
+ "transformer.layers.15.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
461
+ "transformer.layers.15.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
462
+ "transformer.layers.15.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
463
+ "transformer.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
464
+ "transformer.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
465
+ "transformer.layers.16.attention.dense.weight": "model-00002-of-00003.safetensors",
466
+ "transformer.layers.16.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
467
+ "transformer.layers.16.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
468
+ "transformer.layers.16.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
469
+ "transformer.layers.16.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
470
+ "transformer.layers.16.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
471
+ "transformer.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
472
+ "transformer.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
473
+ "transformer.layers.17.attention.dense.weight": "model-00002-of-00003.safetensors",
474
+ "transformer.layers.17.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
475
+ "transformer.layers.17.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
476
+ "transformer.layers.17.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
477
+ "transformer.layers.17.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
478
+ "transformer.layers.17.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
479
+ "transformer.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
480
+ "transformer.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
481
+ "transformer.layers.18.attention.dense.weight": "model-00002-of-00003.safetensors",
482
+ "transformer.layers.18.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
483
+ "transformer.layers.18.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
484
+ "transformer.layers.18.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
485
+ "transformer.layers.18.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
486
+ "transformer.layers.18.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
487
+ "transformer.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
488
+ "transformer.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
489
+ "transformer.layers.19.attention.dense.weight": "model-00002-of-00003.safetensors",
490
+ "transformer.layers.19.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
491
+ "transformer.layers.19.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
492
+ "transformer.layers.19.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
493
+ "transformer.layers.19.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
494
+ "transformer.layers.19.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
495
+ "transformer.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
496
+ "transformer.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
497
+ "transformer.layers.2.attention.dense.weight": "model-00001-of-00003.safetensors",
498
+ "transformer.layers.2.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
499
+ "transformer.layers.2.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
500
+ "transformer.layers.2.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
501
+ "transformer.layers.2.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
502
+ "transformer.layers.2.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
503
+ "transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
504
+ "transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
505
+ "transformer.layers.20.attention.dense.weight": "model-00002-of-00003.safetensors",
506
+ "transformer.layers.20.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
507
+ "transformer.layers.20.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
508
+ "transformer.layers.20.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
509
+ "transformer.layers.20.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
510
+ "transformer.layers.20.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
511
+ "transformer.layers.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
512
+ "transformer.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
513
+ "transformer.layers.21.attention.dense.weight": "model-00002-of-00003.safetensors",
514
+ "transformer.layers.21.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
515
+ "transformer.layers.21.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
516
+ "transformer.layers.21.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
517
+ "transformer.layers.21.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
518
+ "transformer.layers.21.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
519
+ "transformer.layers.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
520
+ "transformer.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
521
+ "transformer.layers.22.attention.dense.weight": "model-00002-of-00003.safetensors",
522
+ "transformer.layers.22.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
523
+ "transformer.layers.22.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
524
+ "transformer.layers.22.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
525
+ "transformer.layers.22.mlp.out_proj.weight": "model-00002-of-00003.safetensors",
526
+ "transformer.layers.22.mlp.packed_input_proj.weight": "model-00002-of-00003.safetensors",
527
+ "transformer.layers.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
528
+ "transformer.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
529
+ "transformer.layers.23.attention.dense.weight": "model-00002-of-00003.safetensors",
530
+ "transformer.layers.23.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
531
+ "transformer.layers.23.attention.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
532
+ "transformer.layers.23.attention.rotary_emb.scale": "model-00002-of-00003.safetensors",
533
+ "transformer.layers.23.mlp.out_proj.weight": "model-00003-of-00003.safetensors",
534
+ "transformer.layers.23.mlp.packed_input_proj.weight": "model-00003-of-00003.safetensors",
535
+ "transformer.layers.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
536
+ "transformer.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
537
+ "transformer.layers.24.attention.dense.weight": "model-00003-of-00003.safetensors",
538
+ "transformer.layers.24.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
539
+ "transformer.layers.24.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
540
+ "transformer.layers.24.attention.rotary_emb.scale": "model-00003-of-00003.safetensors",
541
+ "transformer.layers.24.mlp.out_proj.weight": "model-00003-of-00003.safetensors",
542
+ "transformer.layers.24.mlp.packed_input_proj.weight": "model-00003-of-00003.safetensors",
543
+ "transformer.layers.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
544
+ "transformer.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
545
+ "transformer.layers.25.attention.dense.weight": "model-00003-of-00003.safetensors",
546
+ "transformer.layers.25.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
547
+ "transformer.layers.25.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
548
+ "transformer.layers.25.attention.rotary_emb.scale": "model-00003-of-00003.safetensors",
549
+ "transformer.layers.25.mlp.out_proj.weight": "model-00003-of-00003.safetensors",
550
+ "transformer.layers.25.mlp.packed_input_proj.weight": "model-00003-of-00003.safetensors",
551
+ "transformer.layers.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
552
+ "transformer.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
553
+ "transformer.layers.26.attention.dense.weight": "model-00003-of-00003.safetensors",
554
+ "transformer.layers.26.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
555
+ "transformer.layers.26.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
556
+ "transformer.layers.26.attention.rotary_emb.scale": "model-00003-of-00003.safetensors",
557
+ "transformer.layers.26.mlp.out_proj.weight": "model-00003-of-00003.safetensors",
558
+ "transformer.layers.26.mlp.packed_input_proj.weight": "model-00003-of-00003.safetensors",
559
+ "transformer.layers.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
560
+ "transformer.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
561
+ "transformer.layers.27.attention.dense.weight": "model-00003-of-00003.safetensors",
562
+ "transformer.layers.27.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
563
+ "transformer.layers.27.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
564
+ "transformer.layers.27.attention.rotary_emb.scale": "model-00003-of-00003.safetensors",
565
+ "transformer.layers.27.mlp.out_proj.weight": "model-00003-of-00003.safetensors",
566
+ "transformer.layers.27.mlp.packed_input_proj.weight": "model-00003-of-00003.safetensors",
567
+ "transformer.layers.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
568
+ "transformer.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
569
+ "transformer.layers.28.attention.dense.weight": "model-00003-of-00003.safetensors",
570
+ "transformer.layers.28.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
571
+ "transformer.layers.28.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
572
+ "transformer.layers.28.attention.rotary_emb.scale": "model-00003-of-00003.safetensors",
573
+ "transformer.layers.28.mlp.out_proj.weight": "model-00003-of-00003.safetensors",
574
+ "transformer.layers.28.mlp.packed_input_proj.weight": "model-00003-of-00003.safetensors",
575
+ "transformer.layers.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
576
+ "transformer.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
577
+ "transformer.layers.29.attention.dense.weight": "model-00003-of-00003.safetensors",
578
+ "transformer.layers.29.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
579
+ "transformer.layers.29.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
580
+ "transformer.layers.29.attention.rotary_emb.scale": "model-00003-of-00003.safetensors",
581
+ "transformer.layers.29.mlp.out_proj.weight": "model-00003-of-00003.safetensors",
582
+ "transformer.layers.29.mlp.packed_input_proj.weight": "model-00003-of-00003.safetensors",
583
+ "transformer.layers.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
584
+ "transformer.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
585
+ "transformer.layers.3.attention.dense.weight": "model-00001-of-00003.safetensors",
586
+ "transformer.layers.3.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
587
+ "transformer.layers.3.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
588
+ "transformer.layers.3.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
589
+ "transformer.layers.3.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
590
+ "transformer.layers.3.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
591
+ "transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
592
+ "transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
593
+ "transformer.layers.30.attention.dense.weight": "model-00003-of-00003.safetensors",
594
+ "transformer.layers.30.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
595
+ "transformer.layers.30.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
596
+ "transformer.layers.30.attention.rotary_emb.scale": "model-00003-of-00003.safetensors",
597
+ "transformer.layers.30.mlp.out_proj.weight": "model-00003-of-00003.safetensors",
598
+ "transformer.layers.30.mlp.packed_input_proj.weight": "model-00003-of-00003.safetensors",
599
+ "transformer.layers.30.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
600
+ "transformer.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
601
+ "transformer.layers.31.attention.dense.weight": "model-00003-of-00003.safetensors",
602
+ "transformer.layers.31.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
603
+ "transformer.layers.31.attention.rotary_emb.inv_freq": "model-00003-of-00003.safetensors",
604
+ "transformer.layers.31.attention.rotary_emb.scale": "model-00003-of-00003.safetensors",
605
+ "transformer.layers.31.mlp.out_proj.weight": "model-00003-of-00003.safetensors",
606
+ "transformer.layers.31.mlp.packed_input_proj.weight": "model-00003-of-00003.safetensors",
607
+ "transformer.layers.31.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
608
+ "transformer.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
609
+ "transformer.layers.4.attention.dense.weight": "model-00001-of-00003.safetensors",
610
+ "transformer.layers.4.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
611
+ "transformer.layers.4.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
612
+ "transformer.layers.4.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
613
+ "transformer.layers.4.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
614
+ "transformer.layers.4.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
615
+ "transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
616
+ "transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
617
+ "transformer.layers.5.attention.dense.weight": "model-00001-of-00003.safetensors",
618
+ "transformer.layers.5.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
619
+ "transformer.layers.5.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
620
+ "transformer.layers.5.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
621
+ "transformer.layers.5.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
622
+ "transformer.layers.5.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
623
+ "transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
624
+ "transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
625
+ "transformer.layers.6.attention.dense.weight": "model-00001-of-00003.safetensors",
626
+ "transformer.layers.6.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
627
+ "transformer.layers.6.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
628
+ "transformer.layers.6.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
629
+ "transformer.layers.6.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
630
+ "transformer.layers.6.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
631
+ "transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
632
+ "transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
633
+ "transformer.layers.7.attention.dense.weight": "model-00001-of-00003.safetensors",
634
+ "transformer.layers.7.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
635
+ "transformer.layers.7.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
636
+ "transformer.layers.7.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
637
+ "transformer.layers.7.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
638
+ "transformer.layers.7.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
639
+ "transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
640
+ "transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
641
+ "transformer.layers.8.attention.dense.weight": "model-00001-of-00003.safetensors",
642
+ "transformer.layers.8.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
643
+ "transformer.layers.8.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
644
+ "transformer.layers.8.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
645
+ "transformer.layers.8.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
646
+ "transformer.layers.8.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
647
+ "transformer.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
648
+ "transformer.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
649
+ "transformer.layers.9.attention.dense.weight": "model-00001-of-00003.safetensors",
650
+ "transformer.layers.9.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
651
+ "transformer.layers.9.attention.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
652
+ "transformer.layers.9.attention.rotary_emb.scale": "model-00001-of-00003.safetensors",
653
+ "transformer.layers.9.mlp.out_proj.weight": "model-00001-of-00003.safetensors",
654
+ "transformer.layers.9.mlp.packed_input_proj.weight": "model-00001-of-00003.safetensors",
655
+ "transformer.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
656
+ "transformer.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
657
+ "transformer.visual_projection.visual_projection.0.bias": "model-00003-of-00003.safetensors",
658
+ "transformer.visual_projection.visual_projection.0.weight": "model-00003-of-00003.safetensors",
659
+ "transformer.visual_projection.visual_projection.1.bias": "model-00003-of-00003.safetensors",
660
+ "transformer.visual_projection.visual_projection.1.weight": "model-00003-of-00003.safetensors"
661
+ }
662
+ }