Hugging Face's logo

PerceptronAI
/
Isaac-0.1-Base

Image-Text-to-Text
Safetensors
isaac
conversational
custom_code
Model card Files
xet
Community
2

Update config

#3
by philippguevorguian - opened
base: refs/heads/main
←
from: refs/pr/3
Discussion Files changed
+1470
-153630
Files changed (14) hide show
  1. added_tokens.json +0 -28
  2. config.json +91 -7
  3. generation_config.json +1 -1
  4. merges.txt +0 -0
  5. model-00001-of-00003.safetensors +0 -3
  6. model-00002-of-00003.safetensors +0 -3
  7. model-00003-of-00003.safetensors → model.safetensors +2 -2
  8. model.safetensors.index.json +0 -758
  9. modular_isaac.py +0 -0
  10. processor_config.json +29 -199
  11. special_tokens_map.json +0 -31
  12. tokenizer.json +2 -2
  13. tokenizer_config.json +9 -219
  14. vocab.json +0 -0
added_tokens.json DELETED
@@ -1,28 +0,0 @@
1
- {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -55,18 +55,90 @@
55
  "num_key_value_heads": 8,
56
  "pixel_shuffle_scale": 2,
57
  "rms_norm_eps": 1e-06,
58
- "rope_scaling": {
59
- "mrope_interleaved": true,
60
- "mrope_section": null,
61
  "rope_type": "default"
62
  },
63
- "rope_theta": 1000000.0,
64
  "sliding_window": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
  "tie_word_embeddings": false,
66
- "transformers_version": "4.56.1",
67
  "use_cache": true,
68
  "use_sliding_window": false,
69
- "video_patch_size": 16,
70
  "vision_config": {
71
  "attention_dropout": 0.0,
72
  "hidden_act": "gelu_pytorch_tanh",
@@ -74,7 +146,7 @@
74
  "image_size": 256,
75
  "intermediate_size": 4304,
76
  "layer_norm_eps": 1e-06,
77
- "model_type": "pixel_shuffle_siglip2",
78
  "num_attention_heads": 16,
79
  "num_channels": 3,
80
  "num_hidden_layers": 27,
@@ -83,7 +155,19 @@
83
  "pixel_shuffle_scale_factor": 2
84
  },
85
  "vision_max_num_patches": 6144,
 
 
 
 
 
86
  "vision_min_num_patches": 256,
 
 
 
 
 
 
 
87
  "vision_token": "<image>",
88
  "vocab_size": 151936
89
  }
 
55
  "num_key_value_heads": 8,
56
  "pixel_shuffle_scale": 2,
57
  "rms_norm_eps": 1e-06,
58
+ "rope_parameters": {
59
+ "rope_theta": 1000000,
 
60
  "rope_type": "default"
61
  },
62
+ "rope_theta": 1000000,
63
  "sliding_window": null,
64
+ "text_config": {
65
+ "architectures": [
66
+ "IsaacForConditionalGeneration"
67
+ ],
68
+ "attention_bias": false,
69
+ "attention_dropout": 0.0,
70
+ "bos_token_id": 151643,
71
+ "dtype": "float32",
72
+ "eos_token_id": 151645,
73
+ "head_dim": 128,
74
+ "hidden_act": "silu",
75
+ "hidden_size": 2048,
76
+ "initializer_range": 0.02,
77
+ "intermediate_size": 6144,
78
+ "layer_types": [
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention",
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention",
89
+ "full_attention",
90
+ "full_attention",
91
+ "full_attention",
92
+ "full_attention",
93
+ "full_attention",
94
+ "full_attention",
95
+ "full_attention",
96
+ "full_attention",
97
+ "full_attention",
98
+ "full_attention",
99
+ "full_attention",
100
+ "full_attention",
101
+ "full_attention",
102
+ "full_attention",
103
+ "full_attention",
104
+ "full_attention",
105
+ "full_attention",
106
+ "full_attention"
107
+ ],
108
+ "max_position_embeddings": 40960,
109
+ "max_window_layers": 28,
110
+ "model_type": "qwen3",
111
+ "num_attention_heads": 16,
112
+ "num_hidden_layers": 28,
113
+ "num_key_value_heads": 8,
114
+ "pixel_shuffle_scale": 2,
115
+ "rms_norm_eps": 1e-06,
116
+ "rope_parameters": {
117
+ "rope_theta": 1000000,
118
+ "rope_type": "default"
119
+ },
120
+ "sliding_window": null,
121
+ "use_cache": true,
122
+ "use_sliding_window": false,
123
+ "vision_max_num_patches": 6144,
124
+ "vision_mean": [
125
+ 0.5,
126
+ 0.5,
127
+ 0.5
128
+ ],
129
+ "vision_min_num_patches": 256,
130
+ "vision_patch_size": 16,
131
+ "vision_std": [
132
+ 0.5,
133
+ 0.5,
134
+ 0.5
135
+ ],
136
+ "vocab_size": 151936
137
+ },
138
  "tie_word_embeddings": false,
139
+ "transformers_version": "5.0.0.dev0",
140
  "use_cache": true,
141
  "use_sliding_window": false,
 
142
  "vision_config": {
143
  "attention_dropout": 0.0,
144
  "hidden_act": "gelu_pytorch_tanh",
 
146
  "image_size": 256,
147
  "intermediate_size": 4304,
148
  "layer_norm_eps": 1e-06,
149
+ "model_type": "isaac_vision",
150
  "num_attention_heads": 16,
151
  "num_channels": 3,
152
  "num_hidden_layers": 27,
 
155
  "pixel_shuffle_scale_factor": 2
156
  },
157
  "vision_max_num_patches": 6144,
158
+ "vision_mean": [
159
+ 0.5,
160
+ 0.5,
161
+ 0.5
162
+ ],
163
  "vision_min_num_patches": 256,
164
+ "vision_patch_size": 16,
165
+ "vision_rescale_factor": 0.00392156862745098,
166
+ "vision_std": [
167
+ 0.5,
168
+ 0.5,
169
+ 0.5
170
+ ],
171
  "vision_token": "<image>",
172
  "vocab_size": 151936
173
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 151643,
4
  "eos_token_id": 151645,
5
- "transformers_version": "4.56.1"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 151643,
4
  "eos_token_id": 151645,
5
+ "transformers_version": "5.0.0.dev0"
6
  }
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d31217bf5365162ae38b4e6a5b27acff8481ef892e9803874cbb49476d0f501
3
- size 4969539560
 
 
 
 
model-00002-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e133442cabfd18ed5ba13cd21527d0220c78e2989a2778b8849e5835e0995c75
3
- size 4054187824
 
 
 
 
model-00003-of-00003.safetensors → model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d48fec96ee25327332beee7dbd72e4d82a20d8e2c3e7135fcd6ce3bb9229862
3
- size 1244659840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d7a76b77897015695972d1c51841854c659017480c976f98f860c2e70f8aa6
3
+ size 10268395696
model.safetensors.index.json DELETED
@@ -1,758 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_parameters": 2567073008,
4
- "total_size": 10268292032
5
- },
6
- "weight_map": {
7
- "lm_head.weight": "model-00003-of-00003.safetensors",
8
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
27
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
28
- "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
30
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
31
- "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
32
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
36
- "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
37
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
38
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
39
- "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
40
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
41
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
42
- "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
43
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
44
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
45
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
46
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
47
- "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
48
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
49
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
50
- "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
51
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
52
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
53
- "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
54
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
55
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
56
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
57
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
58
- "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
59
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
60
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
61
- "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
62
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
63
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
64
- "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
65
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
66
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
67
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
68
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
69
- "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
70
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
71
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
72
- "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
73
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
74
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
75
- "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
76
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
77
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
78
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
79
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
80
- "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
81
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
82
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
83
- "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
84
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
85
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
86
- "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
87
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
88
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
89
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
90
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
91
- "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
92
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
93
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
94
- "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
95
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
96
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
97
- "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
98
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
99
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
100
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
101
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
102
- "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
103
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
104
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
105
- "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
106
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
107
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
108
- "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
109
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
110
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
111
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
112
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
113
- "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
114
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
115
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
116
- "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
120
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
121
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
123
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
124
- "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
126
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
127
- "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
128
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
129
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
130
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
135
- "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
138
- "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
140
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
142
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
143
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
144
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
145
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
146
- "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
147
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
148
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
149
- "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
150
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
151
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
152
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
153
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
154
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
157
- "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
158
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
159
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
160
- "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
161
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
162
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
163
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
164
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
165
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
166
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
167
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
168
- "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
169
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
170
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
171
- "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
172
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
173
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
174
- "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
175
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
176
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
177
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
178
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
179
- "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
180
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
181
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
182
- "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
183
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
184
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
185
- "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
186
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
187
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
188
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
189
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
190
- "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
191
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
192
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
193
- "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
194
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
195
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
196
- "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
197
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
198
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
199
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
200
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
201
- "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
202
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
203
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
204
- "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
205
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
206
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
207
- "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
208
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
209
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
210
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
211
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
212
- "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
213
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
214
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
215
- "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
216
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
217
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
218
- "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
219
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
220
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
221
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
222
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
223
- "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
224
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
225
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
226
- "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
227
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
228
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
229
- "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
230
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
231
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
232
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
233
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
234
- "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
235
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
236
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
237
- "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
238
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
239
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
240
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
241
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
242
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
243
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
244
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
245
- "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
246
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
248
- "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
249
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
- "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
257
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
258
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
259
- "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
260
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
261
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
262
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
263
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
264
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
265
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
266
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
267
- "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
268
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
269
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
270
- "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
271
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
272
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
273
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
274
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
275
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
276
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
277
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
278
- "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
279
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
280
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
281
- "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
282
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
283
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
284
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
285
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
291
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
294
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
296
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
297
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
298
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
299
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
300
- "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
301
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
302
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
303
- "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
304
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
305
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
306
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
307
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
308
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
309
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
310
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
311
- "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
312
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
313
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
314
- "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
315
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
316
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
317
- "model.norm.weight": "model-00002-of-00003.safetensors",
318
- "model.vision_embedding.0.embeddings.patch_embedding.bias": "model-00002-of-00003.safetensors",
319
- "model.vision_embedding.0.embeddings.patch_embedding.weight": "model-00002-of-00003.safetensors",
320
- "model.vision_embedding.0.embeddings.position_embedding.weight": "model-00002-of-00003.safetensors",
321
- "model.vision_embedding.0.encoder.layers.0.layer_norm1.bias": "model-00002-of-00003.safetensors",
322
- "model.vision_embedding.0.encoder.layers.0.layer_norm1.weight": "model-00002-of-00003.safetensors",
323
- "model.vision_embedding.0.encoder.layers.0.layer_norm2.bias": "model-00002-of-00003.safetensors",
324
- "model.vision_embedding.0.encoder.layers.0.layer_norm2.weight": "model-00002-of-00003.safetensors",
325
- "model.vision_embedding.0.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00003.safetensors",
326
- "model.vision_embedding.0.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00003.safetensors",
327
- "model.vision_embedding.0.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00003.safetensors",
328
- "model.vision_embedding.0.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00003.safetensors",
329
- "model.vision_embedding.0.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
330
- "model.vision_embedding.0.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
331
- "model.vision_embedding.0.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
332
- "model.vision_embedding.0.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
333
- "model.vision_embedding.0.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
334
- "model.vision_embedding.0.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
335
- "model.vision_embedding.0.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
336
- "model.vision_embedding.0.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
337
- "model.vision_embedding.0.encoder.layers.1.layer_norm1.bias": "model-00002-of-00003.safetensors",
338
- "model.vision_embedding.0.encoder.layers.1.layer_norm1.weight": "model-00002-of-00003.safetensors",
339
- "model.vision_embedding.0.encoder.layers.1.layer_norm2.bias": "model-00002-of-00003.safetensors",
340
- "model.vision_embedding.0.encoder.layers.1.layer_norm2.weight": "model-00002-of-00003.safetensors",
341
- "model.vision_embedding.0.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00003.safetensors",
342
- "model.vision_embedding.0.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00003.safetensors",
343
- "model.vision_embedding.0.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00003.safetensors",
344
- "model.vision_embedding.0.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00003.safetensors",
345
- "model.vision_embedding.0.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
346
- "model.vision_embedding.0.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
347
- "model.vision_embedding.0.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
348
- "model.vision_embedding.0.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
349
- "model.vision_embedding.0.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
350
- "model.vision_embedding.0.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
351
- "model.vision_embedding.0.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
352
- "model.vision_embedding.0.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
353
- "model.vision_embedding.0.encoder.layers.10.layer_norm1.bias": "model-00002-of-00003.safetensors",
354
- "model.vision_embedding.0.encoder.layers.10.layer_norm1.weight": "model-00002-of-00003.safetensors",
355
- "model.vision_embedding.0.encoder.layers.10.layer_norm2.bias": "model-00002-of-00003.safetensors",
356
- "model.vision_embedding.0.encoder.layers.10.layer_norm2.weight": "model-00002-of-00003.safetensors",
357
- "model.vision_embedding.0.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00003.safetensors",
358
- "model.vision_embedding.0.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00003.safetensors",
359
- "model.vision_embedding.0.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00003.safetensors",
360
- "model.vision_embedding.0.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00003.safetensors",
361
- "model.vision_embedding.0.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
362
- "model.vision_embedding.0.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
363
- "model.vision_embedding.0.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
364
- "model.vision_embedding.0.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
365
- "model.vision_embedding.0.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
366
- "model.vision_embedding.0.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
367
- "model.vision_embedding.0.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
368
- "model.vision_embedding.0.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
369
- "model.vision_embedding.0.encoder.layers.11.layer_norm1.bias": "model-00002-of-00003.safetensors",
370
- "model.vision_embedding.0.encoder.layers.11.layer_norm1.weight": "model-00002-of-00003.safetensors",
371
- "model.vision_embedding.0.encoder.layers.11.layer_norm2.bias": "model-00002-of-00003.safetensors",
372
- "model.vision_embedding.0.encoder.layers.11.layer_norm2.weight": "model-00002-of-00003.safetensors",
373
- "model.vision_embedding.0.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00003.safetensors",
374
- "model.vision_embedding.0.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00003.safetensors",
375
- "model.vision_embedding.0.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00003.safetensors",
376
- "model.vision_embedding.0.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00003.safetensors",
377
- "model.vision_embedding.0.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
378
- "model.vision_embedding.0.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
379
- "model.vision_embedding.0.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
380
- "model.vision_embedding.0.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
381
- "model.vision_embedding.0.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
382
- "model.vision_embedding.0.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
383
- "model.vision_embedding.0.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
384
- "model.vision_embedding.0.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
385
- "model.vision_embedding.0.encoder.layers.12.layer_norm1.bias": "model-00002-of-00003.safetensors",
386
- "model.vision_embedding.0.encoder.layers.12.layer_norm1.weight": "model-00002-of-00003.safetensors",
387
- "model.vision_embedding.0.encoder.layers.12.layer_norm2.bias": "model-00002-of-00003.safetensors",
388
- "model.vision_embedding.0.encoder.layers.12.layer_norm2.weight": "model-00002-of-00003.safetensors",
389
- "model.vision_embedding.0.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00003.safetensors",
390
- "model.vision_embedding.0.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00003.safetensors",
391
- "model.vision_embedding.0.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00003.safetensors",
392
- "model.vision_embedding.0.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00003.safetensors",
393
- "model.vision_embedding.0.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
394
- "model.vision_embedding.0.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
395
- "model.vision_embedding.0.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
396
- "model.vision_embedding.0.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
397
- "model.vision_embedding.0.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
398
- "model.vision_embedding.0.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
399
- "model.vision_embedding.0.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
400
- "model.vision_embedding.0.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
401
- "model.vision_embedding.0.encoder.layers.13.layer_norm1.bias": "model-00002-of-00003.safetensors",
402
- "model.vision_embedding.0.encoder.layers.13.layer_norm1.weight": "model-00002-of-00003.safetensors",
403
- "model.vision_embedding.0.encoder.layers.13.layer_norm2.bias": "model-00002-of-00003.safetensors",
404
- "model.vision_embedding.0.encoder.layers.13.layer_norm2.weight": "model-00002-of-00003.safetensors",
405
- "model.vision_embedding.0.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00003.safetensors",
406
- "model.vision_embedding.0.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00003.safetensors",
407
- "model.vision_embedding.0.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00003.safetensors",
408
- "model.vision_embedding.0.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00003.safetensors",
409
- "model.vision_embedding.0.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
410
- "model.vision_embedding.0.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
411
- "model.vision_embedding.0.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
412
- "model.vision_embedding.0.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
413
- "model.vision_embedding.0.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
414
- "model.vision_embedding.0.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
415
- "model.vision_embedding.0.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
416
- "model.vision_embedding.0.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
417
- "model.vision_embedding.0.encoder.layers.14.layer_norm1.bias": "model-00002-of-00003.safetensors",
418
- "model.vision_embedding.0.encoder.layers.14.layer_norm1.weight": "model-00002-of-00003.safetensors",
419
- "model.vision_embedding.0.encoder.layers.14.layer_norm2.bias": "model-00002-of-00003.safetensors",
420
- "model.vision_embedding.0.encoder.layers.14.layer_norm2.weight": "model-00002-of-00003.safetensors",
421
- "model.vision_embedding.0.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00003.safetensors",
422
- "model.vision_embedding.0.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00003.safetensors",
423
- "model.vision_embedding.0.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00003.safetensors",
424
- "model.vision_embedding.0.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00003.safetensors",
425
- "model.vision_embedding.0.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
426
- "model.vision_embedding.0.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
427
- "model.vision_embedding.0.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
428
- "model.vision_embedding.0.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
429
- "model.vision_embedding.0.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
430
- "model.vision_embedding.0.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
431
- "model.vision_embedding.0.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
432
- "model.vision_embedding.0.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
433
- "model.vision_embedding.0.encoder.layers.15.layer_norm1.bias": "model-00002-of-00003.safetensors",
434
- "model.vision_embedding.0.encoder.layers.15.layer_norm1.weight": "model-00002-of-00003.safetensors",
435
- "model.vision_embedding.0.encoder.layers.15.layer_norm2.bias": "model-00002-of-00003.safetensors",
436
- "model.vision_embedding.0.encoder.layers.15.layer_norm2.weight": "model-00002-of-00003.safetensors",
437
- "model.vision_embedding.0.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00003.safetensors",
438
- "model.vision_embedding.0.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00003.safetensors",
439
- "model.vision_embedding.0.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00003.safetensors",
440
- "model.vision_embedding.0.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00003.safetensors",
441
- "model.vision_embedding.0.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
442
- "model.vision_embedding.0.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
443
- "model.vision_embedding.0.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
444
- "model.vision_embedding.0.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
445
- "model.vision_embedding.0.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
446
- "model.vision_embedding.0.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
447
- "model.vision_embedding.0.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
448
- "model.vision_embedding.0.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
449
- "model.vision_embedding.0.encoder.layers.16.layer_norm1.bias": "model-00002-of-00003.safetensors",
450
- "model.vision_embedding.0.encoder.layers.16.layer_norm1.weight": "model-00002-of-00003.safetensors",
451
- "model.vision_embedding.0.encoder.layers.16.layer_norm2.bias": "model-00002-of-00003.safetensors",
452
- "model.vision_embedding.0.encoder.layers.16.layer_norm2.weight": "model-00002-of-00003.safetensors",
453
- "model.vision_embedding.0.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00003.safetensors",
454
- "model.vision_embedding.0.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00003.safetensors",
455
- "model.vision_embedding.0.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00003.safetensors",
456
- "model.vision_embedding.0.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00003.safetensors",
457
- "model.vision_embedding.0.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
458
- "model.vision_embedding.0.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
459
- "model.vision_embedding.0.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
460
- "model.vision_embedding.0.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
461
- "model.vision_embedding.0.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
462
- "model.vision_embedding.0.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
463
- "model.vision_embedding.0.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
464
- "model.vision_embedding.0.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
465
- "model.vision_embedding.0.encoder.layers.17.layer_norm1.bias": "model-00002-of-00003.safetensors",
466
- "model.vision_embedding.0.encoder.layers.17.layer_norm1.weight": "model-00002-of-00003.safetensors",
467
- "model.vision_embedding.0.encoder.layers.17.layer_norm2.bias": "model-00002-of-00003.safetensors",
468
- "model.vision_embedding.0.encoder.layers.17.layer_norm2.weight": "model-00002-of-00003.safetensors",
469
- "model.vision_embedding.0.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00003.safetensors",
470
- "model.vision_embedding.0.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00003.safetensors",
471
- "model.vision_embedding.0.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00003.safetensors",
472
- "model.vision_embedding.0.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00003.safetensors",
473
- "model.vision_embedding.0.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
474
- "model.vision_embedding.0.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
475
- "model.vision_embedding.0.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
476
- "model.vision_embedding.0.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
477
- "model.vision_embedding.0.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
478
- "model.vision_embedding.0.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
479
- "model.vision_embedding.0.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
480
- "model.vision_embedding.0.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
481
- "model.vision_embedding.0.encoder.layers.18.layer_norm1.bias": "model-00002-of-00003.safetensors",
482
- "model.vision_embedding.0.encoder.layers.18.layer_norm1.weight": "model-00002-of-00003.safetensors",
483
- "model.vision_embedding.0.encoder.layers.18.layer_norm2.bias": "model-00002-of-00003.safetensors",
484
- "model.vision_embedding.0.encoder.layers.18.layer_norm2.weight": "model-00002-of-00003.safetensors",
485
- "model.vision_embedding.0.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00003.safetensors",
486
- "model.vision_embedding.0.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00003.safetensors",
487
- "model.vision_embedding.0.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00003.safetensors",
488
- "model.vision_embedding.0.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00003.safetensors",
489
- "model.vision_embedding.0.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
490
- "model.vision_embedding.0.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
491
- "model.vision_embedding.0.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
492
- "model.vision_embedding.0.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
493
- "model.vision_embedding.0.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
494
- "model.vision_embedding.0.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
495
- "model.vision_embedding.0.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
496
- "model.vision_embedding.0.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
497
- "model.vision_embedding.0.encoder.layers.19.layer_norm1.bias": "model-00002-of-00003.safetensors",
498
- "model.vision_embedding.0.encoder.layers.19.layer_norm1.weight": "model-00002-of-00003.safetensors",
499
- "model.vision_embedding.0.encoder.layers.19.layer_norm2.bias": "model-00002-of-00003.safetensors",
500
- "model.vision_embedding.0.encoder.layers.19.layer_norm2.weight": "model-00002-of-00003.safetensors",
501
- "model.vision_embedding.0.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00003.safetensors",
502
- "model.vision_embedding.0.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00003.safetensors",
503
- "model.vision_embedding.0.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00003.safetensors",
504
- "model.vision_embedding.0.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00003.safetensors",
505
- "model.vision_embedding.0.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
506
- "model.vision_embedding.0.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
507
- "model.vision_embedding.0.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
508
- "model.vision_embedding.0.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
509
- "model.vision_embedding.0.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
510
- "model.vision_embedding.0.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
511
- "model.vision_embedding.0.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
512
- "model.vision_embedding.0.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
513
- "model.vision_embedding.0.encoder.layers.2.layer_norm1.bias": "model-00002-of-00003.safetensors",
514
- "model.vision_embedding.0.encoder.layers.2.layer_norm1.weight": "model-00002-of-00003.safetensors",
515
- "model.vision_embedding.0.encoder.layers.2.layer_norm2.bias": "model-00002-of-00003.safetensors",
516
- "model.vision_embedding.0.encoder.layers.2.layer_norm2.weight": "model-00002-of-00003.safetensors",
517
- "model.vision_embedding.0.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00003.safetensors",
518
- "model.vision_embedding.0.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00003.safetensors",
519
- "model.vision_embedding.0.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00003.safetensors",
520
- "model.vision_embedding.0.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00003.safetensors",
521
- "model.vision_embedding.0.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
522
- "model.vision_embedding.0.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
523
- "model.vision_embedding.0.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
524
- "model.vision_embedding.0.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
525
- "model.vision_embedding.0.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
526
- "model.vision_embedding.0.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
527
- "model.vision_embedding.0.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
528
- "model.vision_embedding.0.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
529
- "model.vision_embedding.0.encoder.layers.20.layer_norm1.bias": "model-00002-of-00003.safetensors",
530
- "model.vision_embedding.0.encoder.layers.20.layer_norm1.weight": "model-00002-of-00003.safetensors",
531
- "model.vision_embedding.0.encoder.layers.20.layer_norm2.bias": "model-00002-of-00003.safetensors",
532
- "model.vision_embedding.0.encoder.layers.20.layer_norm2.weight": "model-00002-of-00003.safetensors",
533
- "model.vision_embedding.0.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00003.safetensors",
534
- "model.vision_embedding.0.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00003.safetensors",
535
- "model.vision_embedding.0.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00003.safetensors",
536
- "model.vision_embedding.0.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00003.safetensors",
537
- "model.vision_embedding.0.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
538
- "model.vision_embedding.0.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
539
- "model.vision_embedding.0.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
540
- "model.vision_embedding.0.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
541
- "model.vision_embedding.0.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
542
- "model.vision_embedding.0.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
543
- "model.vision_embedding.0.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
544
- "model.vision_embedding.0.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
545
- "model.vision_embedding.0.encoder.layers.21.layer_norm1.bias": "model-00002-of-00003.safetensors",
546
- "model.vision_embedding.0.encoder.layers.21.layer_norm1.weight": "model-00002-of-00003.safetensors",
547
- "model.vision_embedding.0.encoder.layers.21.layer_norm2.bias": "model-00002-of-00003.safetensors",
548
- "model.vision_embedding.0.encoder.layers.21.layer_norm2.weight": "model-00002-of-00003.safetensors",
549
- "model.vision_embedding.0.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00003.safetensors",
550
- "model.vision_embedding.0.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00003.safetensors",
551
- "model.vision_embedding.0.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00003.safetensors",
552
- "model.vision_embedding.0.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00003.safetensors",
553
- "model.vision_embedding.0.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
554
- "model.vision_embedding.0.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
555
- "model.vision_embedding.0.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
556
- "model.vision_embedding.0.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
557
- "model.vision_embedding.0.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
558
- "model.vision_embedding.0.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
559
- "model.vision_embedding.0.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
560
- "model.vision_embedding.0.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
561
- "model.vision_embedding.0.encoder.layers.22.layer_norm1.bias": "model-00002-of-00003.safetensors",
562
- "model.vision_embedding.0.encoder.layers.22.layer_norm1.weight": "model-00002-of-00003.safetensors",
563
- "model.vision_embedding.0.encoder.layers.22.layer_norm2.bias": "model-00002-of-00003.safetensors",
564
- "model.vision_embedding.0.encoder.layers.22.layer_norm2.weight": "model-00002-of-00003.safetensors",
565
- "model.vision_embedding.0.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00003.safetensors",
566
- "model.vision_embedding.0.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00003.safetensors",
567
- "model.vision_embedding.0.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00003.safetensors",
568
- "model.vision_embedding.0.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00003.safetensors",
569
- "model.vision_embedding.0.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
570
- "model.vision_embedding.0.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
571
- "model.vision_embedding.0.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
572
- "model.vision_embedding.0.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
573
- "model.vision_embedding.0.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
574
- "model.vision_embedding.0.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
575
- "model.vision_embedding.0.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
576
- "model.vision_embedding.0.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
577
- "model.vision_embedding.0.encoder.layers.23.layer_norm1.bias": "model-00002-of-00003.safetensors",
578
- "model.vision_embedding.0.encoder.layers.23.layer_norm1.weight": "model-00002-of-00003.safetensors",
579
- "model.vision_embedding.0.encoder.layers.23.layer_norm2.bias": "model-00002-of-00003.safetensors",
580
- "model.vision_embedding.0.encoder.layers.23.layer_norm2.weight": "model-00002-of-00003.safetensors",
581
- "model.vision_embedding.0.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00003.safetensors",
582
- "model.vision_embedding.0.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00003.safetensors",
583
- "model.vision_embedding.0.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00003.safetensors",
584
- "model.vision_embedding.0.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00003.safetensors",
585
- "model.vision_embedding.0.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
586
- "model.vision_embedding.0.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
587
- "model.vision_embedding.0.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
588
- "model.vision_embedding.0.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
589
- "model.vision_embedding.0.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
590
- "model.vision_embedding.0.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
591
- "model.vision_embedding.0.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
592
- "model.vision_embedding.0.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
593
- "model.vision_embedding.0.encoder.layers.24.layer_norm1.bias": "model-00002-of-00003.safetensors",
594
- "model.vision_embedding.0.encoder.layers.24.layer_norm1.weight": "model-00002-of-00003.safetensors",
595
- "model.vision_embedding.0.encoder.layers.24.layer_norm2.bias": "model-00002-of-00003.safetensors",
596
- "model.vision_embedding.0.encoder.layers.24.layer_norm2.weight": "model-00002-of-00003.safetensors",
597
- "model.vision_embedding.0.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00003.safetensors",
598
- "model.vision_embedding.0.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00003.safetensors",
599
- "model.vision_embedding.0.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00003.safetensors",
600
- "model.vision_embedding.0.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00003.safetensors",
601
- "model.vision_embedding.0.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
602
- "model.vision_embedding.0.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
603
- "model.vision_embedding.0.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
604
- "model.vision_embedding.0.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
605
- "model.vision_embedding.0.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
606
- "model.vision_embedding.0.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
607
- "model.vision_embedding.0.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
608
- "model.vision_embedding.0.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
609
- "model.vision_embedding.0.encoder.layers.25.layer_norm1.bias": "model-00002-of-00003.safetensors",
610
- "model.vision_embedding.0.encoder.layers.25.layer_norm1.weight": "model-00002-of-00003.safetensors",
611
- "model.vision_embedding.0.encoder.layers.25.layer_norm2.bias": "model-00002-of-00003.safetensors",
612
- "model.vision_embedding.0.encoder.layers.25.layer_norm2.weight": "model-00002-of-00003.safetensors",
613
- "model.vision_embedding.0.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00003.safetensors",
614
- "model.vision_embedding.0.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00003.safetensors",
615
- "model.vision_embedding.0.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00003.safetensors",
616
- "model.vision_embedding.0.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00003.safetensors",
617
- "model.vision_embedding.0.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
618
- "model.vision_embedding.0.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
619
- "model.vision_embedding.0.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
620
- "model.vision_embedding.0.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
621
- "model.vision_embedding.0.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
622
- "model.vision_embedding.0.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
623
- "model.vision_embedding.0.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
624
- "model.vision_embedding.0.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
625
- "model.vision_embedding.0.encoder.layers.26.layer_norm1.bias": "model-00002-of-00003.safetensors",
626
- "model.vision_embedding.0.encoder.layers.26.layer_norm1.weight": "model-00002-of-00003.safetensors",
627
- "model.vision_embedding.0.encoder.layers.26.layer_norm2.bias": "model-00002-of-00003.safetensors",
628
- "model.vision_embedding.0.encoder.layers.26.layer_norm2.weight": "model-00002-of-00003.safetensors",
629
- "model.vision_embedding.0.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00003.safetensors",
630
- "model.vision_embedding.0.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00003.safetensors",
631
- "model.vision_embedding.0.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00003.safetensors",
632
- "model.vision_embedding.0.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00003.safetensors",
633
- "model.vision_embedding.0.encoder.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
634
- "model.vision_embedding.0.encoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
635
- "model.vision_embedding.0.encoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
636
- "model.vision_embedding.0.encoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
637
- "model.vision_embedding.0.encoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
638
- "model.vision_embedding.0.encoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
639
- "model.vision_embedding.0.encoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
640
- "model.vision_embedding.0.encoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
641
- "model.vision_embedding.0.encoder.layers.3.layer_norm1.bias": "model-00002-of-00003.safetensors",
642
- "model.vision_embedding.0.encoder.layers.3.layer_norm1.weight": "model-00002-of-00003.safetensors",
643
- "model.vision_embedding.0.encoder.layers.3.layer_norm2.bias": "model-00002-of-00003.safetensors",
644
- "model.vision_embedding.0.encoder.layers.3.layer_norm2.weight": "model-00002-of-00003.safetensors",
645
- "model.vision_embedding.0.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00003.safetensors",
646
- "model.vision_embedding.0.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00003.safetensors",
647
- "model.vision_embedding.0.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00003.safetensors",
648
- "model.vision_embedding.0.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00003.safetensors",
649
- "model.vision_embedding.0.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
650
- "model.vision_embedding.0.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
651
- "model.vision_embedding.0.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
652
- "model.vision_embedding.0.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
653
- "model.vision_embedding.0.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
654
- "model.vision_embedding.0.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
655
- "model.vision_embedding.0.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
656
- "model.vision_embedding.0.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
657
- "model.vision_embedding.0.encoder.layers.4.layer_norm1.bias": "model-00002-of-00003.safetensors",
658
- "model.vision_embedding.0.encoder.layers.4.layer_norm1.weight": "model-00002-of-00003.safetensors",
659
- "model.vision_embedding.0.encoder.layers.4.layer_norm2.bias": "model-00002-of-00003.safetensors",
660
- "model.vision_embedding.0.encoder.layers.4.layer_norm2.weight": "model-00002-of-00003.safetensors",
661
- "model.vision_embedding.0.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00003.safetensors",
662
- "model.vision_embedding.0.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00003.safetensors",
663
- "model.vision_embedding.0.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00003.safetensors",
664
- "model.vision_embedding.0.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00003.safetensors",
665
- "model.vision_embedding.0.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
666
- "model.vision_embedding.0.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
667
- "model.vision_embedding.0.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
668
- "model.vision_embedding.0.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
669
- "model.vision_embedding.0.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
670
- "model.vision_embedding.0.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
671
- "model.vision_embedding.0.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
672
- "model.vision_embedding.0.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
673
- "model.vision_embedding.0.encoder.layers.5.layer_norm1.bias": "model-00002-of-00003.safetensors",
674
- "model.vision_embedding.0.encoder.layers.5.layer_norm1.weight": "model-00002-of-00003.safetensors",
675
- "model.vision_embedding.0.encoder.layers.5.layer_norm2.bias": "model-00002-of-00003.safetensors",
676
- "model.vision_embedding.0.encoder.layers.5.layer_norm2.weight": "model-00002-of-00003.safetensors",
677
- "model.vision_embedding.0.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00003.safetensors",
678
- "model.vision_embedding.0.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00003.safetensors",
679
- "model.vision_embedding.0.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00003.safetensors",
680
- "model.vision_embedding.0.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00003.safetensors",
681
- "model.vision_embedding.0.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
682
- "model.vision_embedding.0.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
683
- "model.vision_embedding.0.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
684
- "model.vision_embedding.0.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
685
- "model.vision_embedding.0.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
686
- "model.vision_embedding.0.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
687
- "model.vision_embedding.0.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
688
- "model.vision_embedding.0.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
689
- "model.vision_embedding.0.encoder.layers.6.layer_norm1.bias": "model-00002-of-00003.safetensors",
690
- "model.vision_embedding.0.encoder.layers.6.layer_norm1.weight": "model-00002-of-00003.safetensors",
691
- "model.vision_embedding.0.encoder.layers.6.layer_norm2.bias": "model-00002-of-00003.safetensors",
692
- "model.vision_embedding.0.encoder.layers.6.layer_norm2.weight": "model-00002-of-00003.safetensors",
693
- "model.vision_embedding.0.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00003.safetensors",
694
- "model.vision_embedding.0.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00003.safetensors",
695
- "model.vision_embedding.0.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00003.safetensors",
696
- "model.vision_embedding.0.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00003.safetensors",
697
- "model.vision_embedding.0.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
698
- "model.vision_embedding.0.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
699
- "model.vision_embedding.0.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
700
- "model.vision_embedding.0.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
701
- "model.vision_embedding.0.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
702
- "model.vision_embedding.0.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
703
- "model.vision_embedding.0.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
704
- "model.vision_embedding.0.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
705
- "model.vision_embedding.0.encoder.layers.7.layer_norm1.bias": "model-00002-of-00003.safetensors",
706
- "model.vision_embedding.0.encoder.layers.7.layer_norm1.weight": "model-00002-of-00003.safetensors",
707
- "model.vision_embedding.0.encoder.layers.7.layer_norm2.bias": "model-00002-of-00003.safetensors",
708
- "model.vision_embedding.0.encoder.layers.7.layer_norm2.weight": "model-00002-of-00003.safetensors",
709
- "model.vision_embedding.0.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00003.safetensors",
710
- "model.vision_embedding.0.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00003.safetensors",
711
- "model.vision_embedding.0.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00003.safetensors",
712
- "model.vision_embedding.0.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00003.safetensors",
713
- "model.vision_embedding.0.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
714
- "model.vision_embedding.0.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
715
- "model.vision_embedding.0.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
716
- "model.vision_embedding.0.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
717
- "model.vision_embedding.0.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
718
- "model.vision_embedding.0.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
719
- "model.vision_embedding.0.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
720
- "model.vision_embedding.0.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
721
- "model.vision_embedding.0.encoder.layers.8.layer_norm1.bias": "model-00002-of-00003.safetensors",
722
- "model.vision_embedding.0.encoder.layers.8.layer_norm1.weight": "model-00002-of-00003.safetensors",
723
- "model.vision_embedding.0.encoder.layers.8.layer_norm2.bias": "model-00002-of-00003.safetensors",
724
- "model.vision_embedding.0.encoder.layers.8.layer_norm2.weight": "model-00002-of-00003.safetensors",
725
- "model.vision_embedding.0.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00003.safetensors",
726
- "model.vision_embedding.0.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00003.safetensors",
727
- "model.vision_embedding.0.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00003.safetensors",
728
- "model.vision_embedding.0.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00003.safetensors",
729
- "model.vision_embedding.0.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
730
- "model.vision_embedding.0.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
731
- "model.vision_embedding.0.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
732
- "model.vision_embedding.0.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
733
- "model.vision_embedding.0.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
734
- "model.vision_embedding.0.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
735
- "model.vision_embedding.0.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
736
- "model.vision_embedding.0.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
737
- "model.vision_embedding.0.encoder.layers.9.layer_norm1.bias": "model-00002-of-00003.safetensors",
738
- "model.vision_embedding.0.encoder.layers.9.layer_norm1.weight": "model-00002-of-00003.safetensors",
739
- "model.vision_embedding.0.encoder.layers.9.layer_norm2.bias": "model-00002-of-00003.safetensors",
740
- "model.vision_embedding.0.encoder.layers.9.layer_norm2.weight": "model-00002-of-00003.safetensors",
741
- "model.vision_embedding.0.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00003.safetensors",
742
- "model.vision_embedding.0.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00003.safetensors",
743
- "model.vision_embedding.0.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00003.safetensors",
744
- "model.vision_embedding.0.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00003.safetensors",
745
- "model.vision_embedding.0.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
746
- "model.vision_embedding.0.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
747
- "model.vision_embedding.0.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
748
- "model.vision_embedding.0.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
749
- "model.vision_embedding.0.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
750
- "model.vision_embedding.0.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
751
- "model.vision_embedding.0.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
752
- "model.vision_embedding.0.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
753
- "model.vision_embedding.0.post_layernorm.bias": "model-00002-of-00003.safetensors",
754
- "model.vision_embedding.0.post_layernorm.weight": "model-00002-of-00003.safetensors",
755
- "model.vision_embedding.1.weight": "model-00002-of-00003.safetensors",
756
- "model.vision_embedding.3.weight": "model-00002-of-00003.safetensors"
757
- }
758
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modular_isaac.py CHANGED
The diff for this file is too large to render. See raw diff
 
processor_config.json CHANGED
@@ -2,208 +2,38 @@
2
  "auto_map": {
3
  "AutoProcessor": "modular_isaac.IsaacProcessor"
4
  },
5
- "config": {
6
- "_name_or_path": "",
7
- "add_cross_attention": false,
8
- "architectures": [
9
- "IsaacForConditionalGeneration"
10
- ],
11
- "attention_bias": false,
12
- "attention_dropout": 0.0,
13
  "auto_map": {
14
- "AutoModelForCausalLM": "modular_isaac.IsaacForConditionalGeneration"
15
- },
16
- "bad_words_ids": null,
17
- "begin_suppress_tokens": null,
18
- "bos_token_id": 151643,
19
- "chunk_size_feed_forward": 0,
20
- "cross_attention_hidden_size": null,
21
- "decoder_start_token_id": null,
22
- "diversity_penalty": 0.0,
23
- "do_sample": false,
24
- "dtype": "float32",
25
- "early_stopping": false,
26
- "encoder_no_repeat_ngram_size": 0,
27
- "eos_token_id": 151645,
28
- "exponential_decay_length_penalty": null,
29
- "finetuning_task": null,
30
- "forced_bos_token_id": null,
31
- "forced_eos_token_id": null,
32
- "head_dim": 128,
33
- "hidden_act": "silu",
34
- "hidden_size": 2048,
35
- "id2label": {
36
- "0": "LABEL_0",
37
- "1": "LABEL_1"
38
- },
39
- "initializer_range": 0.02,
40
- "intermediate_size": 6144,
41
- "is_decoder": false,
42
- "is_encoder_decoder": false,
43
- "label2id": {
44
- "LABEL_0": 0,
45
- "LABEL_1": 1
46
  },
47
- "layer_types": [
48
- "full_attention",
49
- "full_attention",
50
- "full_attention",
51
- "full_attention",
52
- "full_attention",
53
- "full_attention",
54
- "full_attention",
55
- "full_attention",
56
- "full_attention",
57
- "full_attention",
58
- "full_attention",
59
- "full_attention",
60
- "full_attention",
61
- "full_attention",
62
- "full_attention",
63
- "full_attention",
64
- "full_attention",
65
- "full_attention",
66
- "full_attention",
67
- "full_attention",
68
- "full_attention",
69
- "full_attention",
70
- "full_attention",
71
- "full_attention",
72
- "full_attention",
73
- "full_attention",
74
- "full_attention",
75
- "full_attention"
76
  ],
77
- "length_penalty": 1.0,
78
- "max_length": 20,
79
- "max_position_embeddings": 40960,
80
- "max_sequence_length": 16384,
81
- "max_window_layers": 28,
82
- "min_length": 0,
83
- "model_type": "isaac",
84
- "no_repeat_ngram_size": 0,
85
- "num_attention_heads": 16,
86
- "num_beam_groups": 1,
87
- "num_beams": 1,
88
- "num_hidden_layers": 28,
89
- "num_key_value_heads": 8,
90
- "num_return_sequences": 1,
91
- "output_attentions": false,
92
- "output_hidden_states": false,
93
- "output_scores": false,
94
- "pad_token_id": null,
95
  "pixel_shuffle_scale": 2,
96
- "prefix": null,
97
- "problem_type": null,
98
- "pruned_heads": {},
99
- "remove_invalid_values": false,
100
- "repetition_penalty": 1.0,
101
- "return_dict": true,
102
- "return_dict_in_generate": false,
103
- "rms_norm_eps": 1e-06,
104
- "rope_scaling": {
105
- "mrope_interleaved": true,
106
- "mrope_section": null,
107
- "rope_type": "default"
108
- },
109
- "rope_theta": 1000000.0,
110
- "sep_token_id": null,
111
- "sliding_window": null,
112
- "suppress_tokens": null,
113
- "task_specific_params": null,
114
- "temperature": 1.0,
115
- "tf_legacy_loss": false,
116
- "tie_encoder_decoder": false,
117
- "tie_word_embeddings": false,
118
- "tokenizer_class": null,
119
- "top_k": 50,
120
- "top_p": 1.0,
121
- "torchscript": false,
122
- "transformers_version": "4.56.1",
123
- "typical_p": 1.0,
124
- "use_bfloat16": false,
125
- "use_cache": true,
126
- "use_sliding_window": false,
127
- "video_patch_size": 16,
128
- "vision_config": {
129
- "_name_or_path": "",
130
- "add_cross_attention": false,
131
- "architectures": null,
132
- "attention_dropout": 0.0,
133
- "bad_words_ids": null,
134
- "begin_suppress_tokens": null,
135
- "bos_token_id": null,
136
- "chunk_size_feed_forward": 0,
137
- "cross_attention_hidden_size": null,
138
- "decoder_start_token_id": null,
139
- "diversity_penalty": 0.0,
140
- "do_sample": false,
141
- "dtype": null,
142
- "early_stopping": false,
143
- "encoder_no_repeat_ngram_size": 0,
144
- "eos_token_id": null,
145
- "exponential_decay_length_penalty": null,
146
- "finetuning_task": null,
147
- "forced_bos_token_id": null,
148
- "forced_eos_token_id": null,
149
- "hidden_act": "gelu_pytorch_tanh",
150
- "hidden_size": 1152,
151
- "id2label": {
152
- "0": "LABEL_0",
153
- "1": "LABEL_1"
154
- },
155
- "image_size": 256,
156
- "intermediate_size": 4304,
157
- "is_decoder": false,
158
- "is_encoder_decoder": false,
159
- "label2id": {
160
- "LABEL_0": 0,
161
- "LABEL_1": 1
162
- },
163
- "layer_norm_eps": 1e-06,
164
- "length_penalty": 1.0,
165
- "max_length": 20,
166
- "min_length": 0,
167
- "model_type": "pixel_shuffle_siglip2",
168
- "no_repeat_ngram_size": 0,
169
- "num_attention_heads": 16,
170
- "num_beam_groups": 1,
171
- "num_beams": 1,
172
- "num_channels": 3,
173
- "num_hidden_layers": 27,
174
- "num_patches": 256,
175
- "num_return_sequences": 1,
176
- "output_attentions": false,
177
- "output_hidden_states": false,
178
- "output_scores": false,
179
- "pad_token_id": null,
180
- "patch_size": 16,
181
- "pixel_shuffle_scale_factor": 2,
182
- "prefix": null,
183
- "problem_type": null,
184
- "pruned_heads": {},
185
- "remove_invalid_values": false,
186
- "repetition_penalty": 1.0,
187
- "return_dict": true,
188
- "return_dict_in_generate": false,
189
- "sep_token_id": null,
190
- "suppress_tokens": null,
191
- "task_specific_params": null,
192
- "temperature": 1.0,
193
- "tf_legacy_loss": false,
194
- "tie_encoder_decoder": false,
195
- "tie_word_embeddings": true,
196
- "tokenizer_class": null,
197
- "top_k": 50,
198
- "top_p": 1.0,
199
- "torchscript": false,
200
- "typical_p": 1.0,
201
- "use_bfloat16": false
202
- },
203
- "vision_max_num_patches": 6144,
204
- "vision_min_num_patches": 256,
205
- "vision_token": "<image>",
206
- "vocab_size": 151936
207
  },
208
- "processor_class": "IsaacProcessor"
 
 
209
  }
 
2
  "auto_map": {
3
  "AutoProcessor": "modular_isaac.IsaacProcessor"
4
  },
5
+ "config": null,
6
+ "image_processor": {
 
 
 
 
 
 
7
  "auto_map": {
8
+ "AutoProcessor": "modular_isaac.IsaacProcessor"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
10
+ "data_format": "channels_first",
11
+ "disable_grouping": false,
12
+ "do_center_crop": false,
13
+ "do_convert_rgb": true,
14
+ "do_normalize": true,
15
+ "do_pad": false,
16
+ "do_rescale": true,
17
+ "do_resize": true,
18
+ "image_mean": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  ],
23
+ "image_processor_type": "IsaacImageProcessorFast",
24
+ "image_std": [
25
+ 0.5,
26
+ 0.5,
27
+ 0.5
28
+ ],
29
+ "max_num_patches": 6144,
30
+ "min_num_patches": 256,
31
+ "patch_size": 16,
 
 
 
 
 
 
 
 
 
32
  "pixel_shuffle_scale": 2,
33
+ "resample": 2,
34
+ "rescale_factor": 0.00392156862745098
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  },
36
+ "max_sequence_length": 16384,
37
+ "processor_class": "IsaacProcessor",
38
+ "vision_token": "<image>"
39
  }
special_tokens_map.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
- "eos_token": {
18
- "content": "<|im_end|>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- },
24
- "pad_token": {
25
- "content": "<|endoftext|>",
26
- "lstrip": false,
27
- "normalized": false,
28
- "rstrip": false,
29
- "single_word": false
30
- }
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6a069d8afc5e4604a1d15db8b4678d9a804bda3991fe2822cf350ec571084f2
3
+ size 11473537
tokenizer_config.json CHANGED
@@ -1,217 +1,14 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "151643": {
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "151644": {
14
- "content": "<|im_start|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "151645": {
22
- "content": "<|im_end|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "151646": {
30
- "content": "<|object_ref_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "151647": {
38
- "content": "<|object_ref_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "151648": {
46
- "content": "<|box_start|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "151649": {
54
- "content": "<|box_end|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "151650": {
62
- "content": "<|quad_start|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "151651": {
70
- "content": "<|quad_end|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "151652": {
78
- "content": "<|vision_start|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "151653": {
86
- "content": "<|vision_end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "151654": {
94
- "content": "<|vision_pad|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "151655": {
102
- "content": "<|image_pad|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "151656": {
110
- "content": "<|video_pad|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "151657": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "151658": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "151659": {
134
- "content": "<|fim_prefix|>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "151660": {
142
- "content": "<|fim_middle|>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "151661": {
150
- "content": "<|fim_suffix|>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "151662": {
158
- "content": "<|fim_pad|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "151663": {
166
- "content": "<|repo_name|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": false
172
- },
173
- "151664": {
174
- "content": "<|file_sep|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": false
180
- },
181
- "151665": {
182
- "content": "<tool_response>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": false
188
- },
189
- "151666": {
190
- "content": "</tool_response>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": false
196
- },
197
- "151667": {
198
- "content": "<think>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": false
204
- },
205
- "151668": {
206
- "content": "</think>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": false
212
- }
213
  },
214
- "additional_special_tokens": [
 
 
 
 
 
215
  "<|im_start|>",
216
  "<|im_end|>",
217
  "<|object_ref_start|>",
@@ -226,14 +23,7 @@
226
  "<|image_pad|>",
227
  "<|video_pad|>"
228
  ],
229
- "auto_map": {
230
- "AutoProcessor": "modular_isaac.IsaacProcessor"
231
- },
232
- "bos_token": null,
233
- "clean_up_tokenization_spaces": false,
234
- "eos_token": "<|im_end|>",
235
- "errors": "replace",
236
- "extra_special_tokens": {},
237
  "model_max_length": 131072,
238
  "pad_token": "<|endoftext|>",
239
  "processor_class": "IsaacProcessor",
 
1
  {
 
2
  "add_prefix_space": false,
3
+ "auto_map": {
4
+ "AutoProcessor": "modular_isaac.IsaacProcessor"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  },
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "extra_special_tokens": [
12
  "<|im_start|>",
13
  "<|im_end|>",
14
  "<|object_ref_start|>",
 
23
  "<|image_pad|>",
24
  "<|video_pad|>"
25
  ],
26
+ "is_local": true,
 
 
 
 
 
 
 
27
  "model_max_length": 131072,
28
  "pad_token": "<|endoftext|>",
29
  "processor_class": "IsaacProcessor",
vocab.json DELETED
The diff for this file is too large to render. See raw diff