Hugging Face's logo

openvla
/
openvla-7b

Image-Text-to-Text
Transformers
Safetensors
English
openvla
feature-extraction
robotics
vla
multimodal
pretraining
custom_code
Model card Files Community
4
skaramcheti commited on
Commit
cf0c8cb
•
1 Parent(s): 43a4a81

Upload OpenVLAForActionPrediction

Browse files
Files changed (7) hide show
  1. config.json +2 -1
  2. generation_config.json +7 -0
  3. model-00001-of-00003.safetensors +3 -0
  4. model-00002-of-00003.safetensors +3 -0
  5. model-00003-of-00003.safetensors +3 -0
  6. model.safetensors.index.json +989 -0
  7. modeling_prismatic.py +561 -0
config.json CHANGED
@@ -4,7 +4,8 @@
4
  "OpenVLAForActionPrediction"
5
  ],
6
  "auto_map": {
7
- "AutoConfig": "configuration_prismatic.OpenVLAConfig"
 
8
  },
9
  "hf_llm_id": "meta-llama/Llama-2-7b-hf",
10
  "image_resize_strategy": "resize-naive",
 
4
  "OpenVLAForActionPrediction"
5
  ],
6
  "auto_map": {
7
+ "AutoConfig": "configuration_prismatic.OpenVLAConfig",
8
+ "AutoModelForVision2Seq": "modeling_prismatic.OpenVLAForActionPrediction"
9
  },
10
  "hf_llm_id": "meta-llama/Llama-2-7b-hf",
11
  "image_resize_strategy": "resize-naive",
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 32000,
6
+ "transformers_version": "4.40.1"
7
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10d8636256018712c5e5c823d12e22b5797f99bb721bd123bf6bf2379892be85
3
+ size 6948961960
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2050b14f21d48904d269f48d5a980fecea87cd7b36641d9b0f015e72d1fe216a
3
+ size 6971232040
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea65305a1577f36f721965bf84c8caec0a948ce7ce84d754701637376c531fef
3
+ size 1162406824
model.safetensors.index.json ADDED
@@ -0,0 +1,989 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15082474368
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
36
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
37
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
39
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
40
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
47
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
50
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
51
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
52
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
53
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
153
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
154
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
157
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
162
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
163
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
164
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
165
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
166
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
167
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
168
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
169
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
170
+ "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
171
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
172
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
173
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
174
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
175
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
176
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
177
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
178
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
179
+ "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
180
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
181
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
182
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
183
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
185
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
186
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
187
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
188
+ "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
189
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
190
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
191
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
192
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
193
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
194
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
195
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
196
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
197
+ "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
198
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
199
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
200
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
201
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
202
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
203
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
204
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
205
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
206
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
209
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
210
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
212
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
213
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
214
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
215
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
297
+ "projector.fc1.bias": "model-00001-of-00003.safetensors",
298
+ "projector.fc1.weight": "model-00001-of-00003.safetensors",
299
+ "projector.fc2.bias": "model-00001-of-00003.safetensors",
300
+ "projector.fc2.weight": "model-00001-of-00003.safetensors",
301
+ "projector.fc3.bias": "model-00001-of-00003.safetensors",
302
+ "projector.fc3.weight": "model-00001-of-00003.safetensors",
303
+ "vision_backbone.featurizer.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
304
+ "vision_backbone.featurizer.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
305
+ "vision_backbone.featurizer.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
306
+ "vision_backbone.featurizer.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
307
+ "vision_backbone.featurizer.blocks.0.ls1.scale_factor": "model-00001-of-00003.safetensors",
308
+ "vision_backbone.featurizer.blocks.0.ls2.scale_factor": "model-00001-of-00003.safetensors",
309
+ "vision_backbone.featurizer.blocks.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
310
+ "vision_backbone.featurizer.blocks.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
311
+ "vision_backbone.featurizer.blocks.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
312
+ "vision_backbone.featurizer.blocks.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
313
+ "vision_backbone.featurizer.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
314
+ "vision_backbone.featurizer.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
315
+ "vision_backbone.featurizer.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
316
+ "vision_backbone.featurizer.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
317
+ "vision_backbone.featurizer.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
318
+ "vision_backbone.featurizer.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
319
+ "vision_backbone.featurizer.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
320
+ "vision_backbone.featurizer.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
321
+ "vision_backbone.featurizer.blocks.1.ls1.scale_factor": "model-00001-of-00003.safetensors",
322
+ "vision_backbone.featurizer.blocks.1.ls2.scale_factor": "model-00001-of-00003.safetensors",
323
+ "vision_backbone.featurizer.blocks.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
324
+ "vision_backbone.featurizer.blocks.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
325
+ "vision_backbone.featurizer.blocks.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
326
+ "vision_backbone.featurizer.blocks.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
327
+ "vision_backbone.featurizer.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
328
+ "vision_backbone.featurizer.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
329
+ "vision_backbone.featurizer.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
330
+ "vision_backbone.featurizer.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
331
+ "vision_backbone.featurizer.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
332
+ "vision_backbone.featurizer.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
333
+ "vision_backbone.featurizer.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
334
+ "vision_backbone.featurizer.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
335
+ "vision_backbone.featurizer.blocks.10.ls1.scale_factor": "model-00001-of-00003.safetensors",
336
+ "vision_backbone.featurizer.blocks.10.ls2.scale_factor": "model-00001-of-00003.safetensors",
337
+ "vision_backbone.featurizer.blocks.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
338
+ "vision_backbone.featurizer.blocks.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
339
+ "vision_backbone.featurizer.blocks.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
340
+ "vision_backbone.featurizer.blocks.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
341
+ "vision_backbone.featurizer.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
342
+ "vision_backbone.featurizer.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
343
+ "vision_backbone.featurizer.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
344
+ "vision_backbone.featurizer.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
345
+ "vision_backbone.featurizer.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
346
+ "vision_backbone.featurizer.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
347
+ "vision_backbone.featurizer.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
348
+ "vision_backbone.featurizer.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
349
+ "vision_backbone.featurizer.blocks.11.ls1.scale_factor": "model-00001-of-00003.safetensors",
350
+ "vision_backbone.featurizer.blocks.11.ls2.scale_factor": "model-00001-of-00003.safetensors",
351
+ "vision_backbone.featurizer.blocks.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
352
+ "vision_backbone.featurizer.blocks.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
353
+ "vision_backbone.featurizer.blocks.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
354
+ "vision_backbone.featurizer.blocks.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
355
+ "vision_backbone.featurizer.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
356
+ "vision_backbone.featurizer.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
357
+ "vision_backbone.featurizer.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
358
+ "vision_backbone.featurizer.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
359
+ "vision_backbone.featurizer.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
360
+ "vision_backbone.featurizer.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
361
+ "vision_backbone.featurizer.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
362
+ "vision_backbone.featurizer.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
363
+ "vision_backbone.featurizer.blocks.12.ls1.scale_factor": "model-00001-of-00003.safetensors",
364
+ "vision_backbone.featurizer.blocks.12.ls2.scale_factor": "model-00001-of-00003.safetensors",
365
+ "vision_backbone.featurizer.blocks.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
366
+ "vision_backbone.featurizer.blocks.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
367
+ "vision_backbone.featurizer.blocks.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
368
+ "vision_backbone.featurizer.blocks.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
369
+ "vision_backbone.featurizer.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
370
+ "vision_backbone.featurizer.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
371
+ "vision_backbone.featurizer.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
372
+ "vision_backbone.featurizer.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
373
+ "vision_backbone.featurizer.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
374
+ "vision_backbone.featurizer.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
375
+ "vision_backbone.featurizer.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
376
+ "vision_backbone.featurizer.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
377
+ "vision_backbone.featurizer.blocks.13.ls1.scale_factor": "model-00001-of-00003.safetensors",
378
+ "vision_backbone.featurizer.blocks.13.ls2.scale_factor": "model-00001-of-00003.safetensors",
379
+ "vision_backbone.featurizer.blocks.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
380
+ "vision_backbone.featurizer.blocks.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
381
+ "vision_backbone.featurizer.blocks.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
382
+ "vision_backbone.featurizer.blocks.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
383
+ "vision_backbone.featurizer.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
384
+ "vision_backbone.featurizer.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
385
+ "vision_backbone.featurizer.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
386
+ "vision_backbone.featurizer.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
387
+ "vision_backbone.featurizer.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
388
+ "vision_backbone.featurizer.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
389
+ "vision_backbone.featurizer.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
390
+ "vision_backbone.featurizer.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
391
+ "vision_backbone.featurizer.blocks.14.ls1.scale_factor": "model-00001-of-00003.safetensors",
392
+ "vision_backbone.featurizer.blocks.14.ls2.scale_factor": "model-00001-of-00003.safetensors",
393
+ "vision_backbone.featurizer.blocks.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
394
+ "vision_backbone.featurizer.blocks.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
395
+ "vision_backbone.featurizer.blocks.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
396
+ "vision_backbone.featurizer.blocks.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
397
+ "vision_backbone.featurizer.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
398
+ "vision_backbone.featurizer.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
399
+ "vision_backbone.featurizer.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
400
+ "vision_backbone.featurizer.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
401
+ "vision_backbone.featurizer.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
402
+ "vision_backbone.featurizer.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
403
+ "vision_backbone.featurizer.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
404
+ "vision_backbone.featurizer.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
405
+ "vision_backbone.featurizer.blocks.15.ls1.scale_factor": "model-00001-of-00003.safetensors",
406
+ "vision_backbone.featurizer.blocks.15.ls2.scale_factor": "model-00001-of-00003.safetensors",
407
+ "vision_backbone.featurizer.blocks.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
408
+ "vision_backbone.featurizer.blocks.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
409
+ "vision_backbone.featurizer.blocks.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
410
+ "vision_backbone.featurizer.blocks.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
411
+ "vision_backbone.featurizer.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
412
+ "vision_backbone.featurizer.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
413
+ "vision_backbone.featurizer.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
414
+ "vision_backbone.featurizer.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
415
+ "vision_backbone.featurizer.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
416
+ "vision_backbone.featurizer.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
417
+ "vision_backbone.featurizer.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
418
+ "vision_backbone.featurizer.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
419
+ "vision_backbone.featurizer.blocks.16.ls1.scale_factor": "model-00001-of-00003.safetensors",
420
+ "vision_backbone.featurizer.blocks.16.ls2.scale_factor": "model-00001-of-00003.safetensors",
421
+ "vision_backbone.featurizer.blocks.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
422
+ "vision_backbone.featurizer.blocks.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
423
+ "vision_backbone.featurizer.blocks.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
424
+ "vision_backbone.featurizer.blocks.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
425
+ "vision_backbone.featurizer.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
426
+ "vision_backbone.featurizer.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
427
+ "vision_backbone.featurizer.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
428
+ "vision_backbone.featurizer.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
429
+ "vision_backbone.featurizer.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
430
+ "vision_backbone.featurizer.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
431
+ "vision_backbone.featurizer.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
432
+ "vision_backbone.featurizer.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
433
+ "vision_backbone.featurizer.blocks.17.ls1.scale_factor": "model-00001-of-00003.safetensors",
434
+ "vision_backbone.featurizer.blocks.17.ls2.scale_factor": "model-00001-of-00003.safetensors",
435
+ "vision_backbone.featurizer.blocks.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
436
+ "vision_backbone.featurizer.blocks.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
437
+ "vision_backbone.featurizer.blocks.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
438
+ "vision_backbone.featurizer.blocks.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
439
+ "vision_backbone.featurizer.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
440
+ "vision_backbone.featurizer.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
441
+ "vision_backbone.featurizer.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
442
+ "vision_backbone.featurizer.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
443
+ "vision_backbone.featurizer.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
444
+ "vision_backbone.featurizer.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
445
+ "vision_backbone.featurizer.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
446
+ "vision_backbone.featurizer.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
447
+ "vision_backbone.featurizer.blocks.18.ls1.scale_factor": "model-00001-of-00003.safetensors",
448
+ "vision_backbone.featurizer.blocks.18.ls2.scale_factor": "model-00001-of-00003.safetensors",
449
+ "vision_backbone.featurizer.blocks.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
450
+ "vision_backbone.featurizer.blocks.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
451
+ "vision_backbone.featurizer.blocks.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
452
+ "vision_backbone.featurizer.blocks.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
453
+ "vision_backbone.featurizer.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
454
+ "vision_backbone.featurizer.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
455
+ "vision_backbone.featurizer.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
456
+ "vision_backbone.featurizer.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
457
+ "vision_backbone.featurizer.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
458
+ "vision_backbone.featurizer.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
459
+ "vision_backbone.featurizer.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
460
+ "vision_backbone.featurizer.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
461
+ "vision_backbone.featurizer.blocks.19.ls1.scale_factor": "model-00001-of-00003.safetensors",
462
+ "vision_backbone.featurizer.blocks.19.ls2.scale_factor": "model-00001-of-00003.safetensors",
463
+ "vision_backbone.featurizer.blocks.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
464
+ "vision_backbone.featurizer.blocks.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
465
+ "vision_backbone.featurizer.blocks.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
466
+ "vision_backbone.featurizer.blocks.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
467
+ "vision_backbone.featurizer.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
468
+ "vision_backbone.featurizer.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
469
+ "vision_backbone.featurizer.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
470
+ "vision_backbone.featurizer.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
471
+ "vision_backbone.featurizer.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
472
+ "vision_backbone.featurizer.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
473
+ "vision_backbone.featurizer.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
474
+ "vision_backbone.featurizer.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
475
+ "vision_backbone.featurizer.blocks.2.ls1.scale_factor": "model-00001-of-00003.safetensors",
476
+ "vision_backbone.featurizer.blocks.2.ls2.scale_factor": "model-00001-of-00003.safetensors",
477
+ "vision_backbone.featurizer.blocks.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
478
+ "vision_backbone.featurizer.blocks.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
479
+ "vision_backbone.featurizer.blocks.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
480
+ "vision_backbone.featurizer.blocks.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
481
+ "vision_backbone.featurizer.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
482
+ "vision_backbone.featurizer.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
483
+ "vision_backbone.featurizer.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
484
+ "vision_backbone.featurizer.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
485
+ "vision_backbone.featurizer.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
486
+ "vision_backbone.featurizer.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
487
+ "vision_backbone.featurizer.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
488
+ "vision_backbone.featurizer.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
489
+ "vision_backbone.featurizer.blocks.20.ls1.scale_factor": "model-00001-of-00003.safetensors",
490
+ "vision_backbone.featurizer.blocks.20.ls2.scale_factor": "model-00001-of-00003.safetensors",
491
+ "vision_backbone.featurizer.blocks.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
492
+ "vision_backbone.featurizer.blocks.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
493
+ "vision_backbone.featurizer.blocks.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
494
+ "vision_backbone.featurizer.blocks.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
495
+ "vision_backbone.featurizer.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
496
+ "vision_backbone.featurizer.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
497
+ "vision_backbone.featurizer.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
498
+ "vision_backbone.featurizer.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
499
+ "vision_backbone.featurizer.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
500
+ "vision_backbone.featurizer.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
501
+ "vision_backbone.featurizer.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
502
+ "vision_backbone.featurizer.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
503
+ "vision_backbone.featurizer.blocks.21.ls1.scale_factor": "model-00001-of-00003.safetensors",
504
+ "vision_backbone.featurizer.blocks.21.ls2.scale_factor": "model-00001-of-00003.safetensors",
505
+ "vision_backbone.featurizer.blocks.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
506
+ "vision_backbone.featurizer.blocks.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
507
+ "vision_backbone.featurizer.blocks.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
508
+ "vision_backbone.featurizer.blocks.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
509
+ "vision_backbone.featurizer.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
510
+ "vision_backbone.featurizer.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
511
+ "vision_backbone.featurizer.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
512
+ "vision_backbone.featurizer.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
513
+ "vision_backbone.featurizer.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
514
+ "vision_backbone.featurizer.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
515
+ "vision_backbone.featurizer.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
516
+ "vision_backbone.featurizer.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
517
+ "vision_backbone.featurizer.blocks.22.ls1.scale_factor": "model-00001-of-00003.safetensors",
518
+ "vision_backbone.featurizer.blocks.22.ls2.scale_factor": "model-00001-of-00003.safetensors",
519
+ "vision_backbone.featurizer.blocks.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
520
+ "vision_backbone.featurizer.blocks.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
521
+ "vision_backbone.featurizer.blocks.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
522
+ "vision_backbone.featurizer.blocks.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
523
+ "vision_backbone.featurizer.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
524
+ "vision_backbone.featurizer.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
525
+ "vision_backbone.featurizer.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
526
+ "vision_backbone.featurizer.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
527
+ "vision_backbone.featurizer.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
528
+ "vision_backbone.featurizer.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
529
+ "vision_backbone.featurizer.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
530
+ "vision_backbone.featurizer.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
531
+ "vision_backbone.featurizer.blocks.23.ls1.scale_factor": "model-00001-of-00003.safetensors",
532
+ "vision_backbone.featurizer.blocks.23.ls2.scale_factor": "model-00001-of-00003.safetensors",
533
+ "vision_backbone.featurizer.blocks.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
534
+ "vision_backbone.featurizer.blocks.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
535
+ "vision_backbone.featurizer.blocks.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
536
+ "vision_backbone.featurizer.blocks.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
537
+ "vision_backbone.featurizer.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
538
+ "vision_backbone.featurizer.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
539
+ "vision_backbone.featurizer.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
540
+ "vision_backbone.featurizer.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
541
+ "vision_backbone.featurizer.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
542
+ "vision_backbone.featurizer.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
543
+ "vision_backbone.featurizer.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
544
+ "vision_backbone.featurizer.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
545
+ "vision_backbone.featurizer.blocks.3.ls1.scale_factor": "model-00001-of-00003.safetensors",
546
+ "vision_backbone.featurizer.blocks.3.ls2.scale_factor": "model-00001-of-00003.safetensors",
547
+ "vision_backbone.featurizer.blocks.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
548
+ "vision_backbone.featurizer.blocks.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
549
+ "vision_backbone.featurizer.blocks.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
550
+ "vision_backbone.featurizer.blocks.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
551
+ "vision_backbone.featurizer.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
552
+ "vision_backbone.featurizer.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
553
+ "vision_backbone.featurizer.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
554
+ "vision_backbone.featurizer.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
555
+ "vision_backbone.featurizer.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
556
+ "vision_backbone.featurizer.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
557
+ "vision_backbone.featurizer.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
558
+ "vision_backbone.featurizer.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
559
+ "vision_backbone.featurizer.blocks.4.ls1.scale_factor": "model-00001-of-00003.safetensors",
560
+ "vision_backbone.featurizer.blocks.4.ls2.scale_factor": "model-00001-of-00003.safetensors",
561
+ "vision_backbone.featurizer.blocks.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
562
+ "vision_backbone.featurizer.blocks.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
563
+ "vision_backbone.featurizer.blocks.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
564
+ "vision_backbone.featurizer.blocks.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
565
+ "vision_backbone.featurizer.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
566
+ "vision_backbone.featurizer.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
567
+ "vision_backbone.featurizer.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
568
+ "vision_backbone.featurizer.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
569
+ "vision_backbone.featurizer.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
570
+ "vision_backbone.featurizer.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
571
+ "vision_backbone.featurizer.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
572
+ "vision_backbone.featurizer.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
573
+ "vision_backbone.featurizer.blocks.5.ls1.scale_factor": "model-00001-of-00003.safetensors",
574
+ "vision_backbone.featurizer.blocks.5.ls2.scale_factor": "model-00001-of-00003.safetensors",
575
+ "vision_backbone.featurizer.blocks.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
576
+ "vision_backbone.featurizer.blocks.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
577
+ "vision_backbone.featurizer.blocks.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
578
+ "vision_backbone.featurizer.blocks.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
579
+ "vision_backbone.featurizer.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
580
+ "vision_backbone.featurizer.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
581
+ "vision_backbone.featurizer.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
582
+ "vision_backbone.featurizer.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
583
+ "vision_backbone.featurizer.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
584
+ "vision_backbone.featurizer.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
585
+ "vision_backbone.featurizer.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
586
+ "vision_backbone.featurizer.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
587
+ "vision_backbone.featurizer.blocks.6.ls1.scale_factor": "model-00001-of-00003.safetensors",
588
+ "vision_backbone.featurizer.blocks.6.ls2.scale_factor": "model-00001-of-00003.safetensors",
589
+ "vision_backbone.featurizer.blocks.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
590
+ "vision_backbone.featurizer.blocks.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
591
+ "vision_backbone.featurizer.blocks.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
592
+ "vision_backbone.featurizer.blocks.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
593
+ "vision_backbone.featurizer.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
594
+ "vision_backbone.featurizer.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
595
+ "vision_backbone.featurizer.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
596
+ "vision_backbone.featurizer.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
597
+ "vision_backbone.featurizer.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
598
+ "vision_backbone.featurizer.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
599
+ "vision_backbone.featurizer.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
600
+ "vision_backbone.featurizer.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
601
+ "vision_backbone.featurizer.blocks.7.ls1.scale_factor": "model-00001-of-00003.safetensors",
602
+ "vision_backbone.featurizer.blocks.7.ls2.scale_factor": "model-00001-of-00003.safetensors",
603
+ "vision_backbone.featurizer.blocks.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
604
+ "vision_backbone.featurizer.blocks.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
605
+ "vision_backbone.featurizer.blocks.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
606
+ "vision_backbone.featurizer.blocks.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
607
+ "vision_backbone.featurizer.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
608
+ "vision_backbone.featurizer.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
609
+ "vision_backbone.featurizer.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
610
+ "vision_backbone.featurizer.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
611
+ "vision_backbone.featurizer.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
612
+ "vision_backbone.featurizer.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
613
+ "vision_backbone.featurizer.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
614
+ "vision_backbone.featurizer.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
615
+ "vision_backbone.featurizer.blocks.8.ls1.scale_factor": "model-00001-of-00003.safetensors",
616
+ "vision_backbone.featurizer.blocks.8.ls2.scale_factor": "model-00001-of-00003.safetensors",
617
+ "vision_backbone.featurizer.blocks.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
618
+ "vision_backbone.featurizer.blocks.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
619
+ "vision_backbone.featurizer.blocks.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
620
+ "vision_backbone.featurizer.blocks.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
621
+ "vision_backbone.featurizer.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
622
+ "vision_backbone.featurizer.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
623
+ "vision_backbone.featurizer.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
624
+ "vision_backbone.featurizer.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
625
+ "vision_backbone.featurizer.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
626
+ "vision_backbone.featurizer.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
627
+ "vision_backbone.featurizer.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
628
+ "vision_backbone.featurizer.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
629
+ "vision_backbone.featurizer.blocks.9.ls1.scale_factor": "model-00001-of-00003.safetensors",
630
+ "vision_backbone.featurizer.blocks.9.ls2.scale_factor": "model-00001-of-00003.safetensors",
631
+ "vision_backbone.featurizer.blocks.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
632
+ "vision_backbone.featurizer.blocks.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
633
+ "vision_backbone.featurizer.blocks.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
634
+ "vision_backbone.featurizer.blocks.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
635
+ "vision_backbone.featurizer.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
636
+ "vision_backbone.featurizer.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
637
+ "vision_backbone.featurizer.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
638
+ "vision_backbone.featurizer.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
639
+ "vision_backbone.featurizer.cls_token": "model-00001-of-00003.safetensors",
640
+ "vision_backbone.featurizer.norm.bias": "model-00001-of-00003.safetensors",
641
+ "vision_backbone.featurizer.norm.weight": "model-00001-of-00003.safetensors",
642
+ "vision_backbone.featurizer.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
643
+ "vision_backbone.featurizer.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
644
+ "vision_backbone.featurizer.pos_embed": "model-00001-of-00003.safetensors",
645
+ "vision_backbone.featurizer.reg_token": "model-00001-of-00003.safetensors",
646
+ "vision_backbone.fused_featurizer.attn_pool.kv.bias": "model-00001-of-00003.safetensors",
647
+ "vision_backbone.fused_featurizer.attn_pool.kv.weight": "model-00001-of-00003.safetensors",
648
+ "vision_backbone.fused_featurizer.attn_pool.latent": "model-00001-of-00003.safetensors",
649
+ "vision_backbone.fused_featurizer.attn_pool.mlp.fc1.bias": "model-00001-of-00003.safetensors",
650
+ "vision_backbone.fused_featurizer.attn_pool.mlp.fc1.weight": "model-00001-of-00003.safetensors",
651
+ "vision_backbone.fused_featurizer.attn_pool.mlp.fc2.bias": "model-00001-of-00003.safetensors",
652
+ "vision_backbone.fused_featurizer.attn_pool.mlp.fc2.weight": "model-00001-of-00003.safetensors",
653
+ "vision_backbone.fused_featurizer.attn_pool.norm.bias": "model-00001-of-00003.safetensors",
654
+ "vision_backbone.fused_featurizer.attn_pool.norm.weight": "model-00001-of-00003.safetensors",
655
+ "vision_backbone.fused_featurizer.attn_pool.proj.bias": "model-00001-of-00003.safetensors",
656
+ "vision_backbone.fused_featurizer.attn_pool.proj.weight": "model-00001-of-00003.safetensors",
657
+ "vision_backbone.fused_featurizer.attn_pool.q.bias": "model-00001-of-00003.safetensors",
658
+ "vision_backbone.fused_featurizer.attn_pool.q.weight": "model-00001-of-00003.safetensors",
659
+ "vision_backbone.fused_featurizer.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
660
+ "vision_backbone.fused_featurizer.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
661
+ "vision_backbone.fused_featurizer.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
662
+ "vision_backbone.fused_featurizer.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
663
+ "vision_backbone.fused_featurizer.blocks.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
664
+ "vision_backbone.fused_featurizer.blocks.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
665
+ "vision_backbone.fused_featurizer.blocks.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
666
+ "vision_backbone.fused_featurizer.blocks.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
667
+ "vision_backbone.fused_featurizer.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
668
+ "vision_backbone.fused_featurizer.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
669
+ "vision_backbone.fused_featurizer.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
670
+ "vision_backbone.fused_featurizer.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
671
+ "vision_backbone.fused_featurizer.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
672
+ "vision_backbone.fused_featurizer.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
673
+ "vision_backbone.fused_featurizer.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
674
+ "vision_backbone.fused_featurizer.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
675
+ "vision_backbone.fused_featurizer.blocks.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
676
+ "vision_backbone.fused_featurizer.blocks.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
677
+ "vision_backbone.fused_featurizer.blocks.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
678
+ "vision_backbone.fused_featurizer.blocks.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
679
+ "vision_backbone.fused_featurizer.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
680
+ "vision_backbone.fused_featurizer.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
681
+ "vision_backbone.fused_featurizer.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
682
+ "vision_backbone.fused_featurizer.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
683
+ "vision_backbone.fused_featurizer.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
684
+ "vision_backbone.fused_featurizer.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
685
+ "vision_backbone.fused_featurizer.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
686
+ "vision_backbone.fused_featurizer.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
687
+ "vision_backbone.fused_featurizer.blocks.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
688
+ "vision_backbone.fused_featurizer.blocks.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
689
+ "vision_backbone.fused_featurizer.blocks.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
690
+ "vision_backbone.fused_featurizer.blocks.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
691
+ "vision_backbone.fused_featurizer.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
692
+ "vision_backbone.fused_featurizer.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
693
+ "vision_backbone.fused_featurizer.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
694
+ "vision_backbone.fused_featurizer.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
695
+ "vision_backbone.fused_featurizer.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
696
+ "vision_backbone.fused_featurizer.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
697
+ "vision_backbone.fused_featurizer.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
698
+ "vision_backbone.fused_featurizer.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
699
+ "vision_backbone.fused_featurizer.blocks.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
700
+ "vision_backbone.fused_featurizer.blocks.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
701
+ "vision_backbone.fused_featurizer.blocks.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
702
+ "vision_backbone.fused_featurizer.blocks.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
703
+ "vision_backbone.fused_featurizer.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
704
+ "vision_backbone.fused_featurizer.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
705
+ "vision_backbone.fused_featurizer.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
706
+ "vision_backbone.fused_featurizer.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
707
+ "vision_backbone.fused_featurizer.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
708
+ "vision_backbone.fused_featurizer.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
709
+ "vision_backbone.fused_featurizer.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
710
+ "vision_backbone.fused_featurizer.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
711
+ "vision_backbone.fused_featurizer.blocks.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
712
+ "vision_backbone.fused_featurizer.blocks.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
713
+ "vision_backbone.fused_featurizer.blocks.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
714
+ "vision_backbone.fused_featurizer.blocks.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
715
+ "vision_backbone.fused_featurizer.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
716
+ "vision_backbone.fused_featurizer.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
717
+ "vision_backbone.fused_featurizer.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
718
+ "vision_backbone.fused_featurizer.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
719
+ "vision_backbone.fused_featurizer.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
720
+ "vision_backbone.fused_featurizer.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
721
+ "vision_backbone.fused_featurizer.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
722
+ "vision_backbone.fused_featurizer.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
723
+ "vision_backbone.fused_featurizer.blocks.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
724
+ "vision_backbone.fused_featurizer.blocks.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
725
+ "vision_backbone.fused_featurizer.blocks.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
726
+ "vision_backbone.fused_featurizer.blocks.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
727
+ "vision_backbone.fused_featurizer.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
728
+ "vision_backbone.fused_featurizer.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
729
+ "vision_backbone.fused_featurizer.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
730
+ "vision_backbone.fused_featurizer.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
731
+ "vision_backbone.fused_featurizer.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
732
+ "vision_backbone.fused_featurizer.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
733
+ "vision_backbone.fused_featurizer.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
734
+ "vision_backbone.fused_featurizer.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
735
+ "vision_backbone.fused_featurizer.blocks.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
736
+ "vision_backbone.fused_featurizer.blocks.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
737
+ "vision_backbone.fused_featurizer.blocks.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
738
+ "vision_backbone.fused_featurizer.blocks.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
739
+ "vision_backbone.fused_featurizer.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
740
+ "vision_backbone.fused_featurizer.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
741
+ "vision_backbone.fused_featurizer.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
742
+ "vision_backbone.fused_featurizer.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
743
+ "vision_backbone.fused_featurizer.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
744
+ "vision_backbone.fused_featurizer.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
745
+ "vision_backbone.fused_featurizer.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
746
+ "vision_backbone.fused_featurizer.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
747
+ "vision_backbone.fused_featurizer.blocks.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
748
+ "vision_backbone.fused_featurizer.blocks.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
749
+ "vision_backbone.fused_featurizer.blocks.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
750
+ "vision_backbone.fused_featurizer.blocks.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
751
+ "vision_backbone.fused_featurizer.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
752
+ "vision_backbone.fused_featurizer.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
753
+ "vision_backbone.fused_featurizer.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
754
+ "vision_backbone.fused_featurizer.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
755
+ "vision_backbone.fused_featurizer.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
756
+ "vision_backbone.fused_featurizer.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
757
+ "vision_backbone.fused_featurizer.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
758
+ "vision_backbone.fused_featurizer.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
759
+ "vision_backbone.fused_featurizer.blocks.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
760
+ "vision_backbone.fused_featurizer.blocks.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
761
+ "vision_backbone.fused_featurizer.blocks.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
762
+ "vision_backbone.fused_featurizer.blocks.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
763
+ "vision_backbone.fused_featurizer.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
764
+ "vision_backbone.fused_featurizer.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
765
+ "vision_backbone.fused_featurizer.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
766
+ "vision_backbone.fused_featurizer.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
767
+ "vision_backbone.fused_featurizer.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
768
+ "vision_backbone.fused_featurizer.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
769
+ "vision_backbone.fused_featurizer.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
770
+ "vision_backbone.fused_featurizer.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
771
+ "vision_backbone.fused_featurizer.blocks.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
772
+ "vision_backbone.fused_featurizer.blocks.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
773
+ "vision_backbone.fused_featurizer.blocks.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
774
+ "vision_backbone.fused_featurizer.blocks.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
775
+ "vision_backbone.fused_featurizer.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
776
+ "vision_backbone.fused_featurizer.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
777
+ "vision_backbone.fused_featurizer.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
778
+ "vision_backbone.fused_featurizer.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
779
+ "vision_backbone.fused_featurizer.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
780
+ "vision_backbone.fused_featurizer.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
781
+ "vision_backbone.fused_featurizer.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
782
+ "vision_backbone.fused_featurizer.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
783
+ "vision_backbone.fused_featurizer.blocks.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
784
+ "vision_backbone.fused_featurizer.blocks.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
785
+ "vision_backbone.fused_featurizer.blocks.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
786
+ "vision_backbone.fused_featurizer.blocks.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
787
+ "vision_backbone.fused_featurizer.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
788
+ "vision_backbone.fused_featurizer.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
789
+ "vision_backbone.fused_featurizer.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
790
+ "vision_backbone.fused_featurizer.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
791
+ "vision_backbone.fused_featurizer.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
792
+ "vision_backbone.fused_featurizer.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
793
+ "vision_backbone.fused_featurizer.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
794
+ "vision_backbone.fused_featurizer.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
795
+ "vision_backbone.fused_featurizer.blocks.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
796
+ "vision_backbone.fused_featurizer.blocks.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
797
+ "vision_backbone.fused_featurizer.blocks.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
798
+ "vision_backbone.fused_featurizer.blocks.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
799
+ "vision_backbone.fused_featurizer.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
800
+ "vision_backbone.fused_featurizer.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
801
+ "vision_backbone.fused_featurizer.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
802
+ "vision_backbone.fused_featurizer.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
803
+ "vision_backbone.fused_featurizer.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
804
+ "vision_backbone.fused_featurizer.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
805
+ "vision_backbone.fused_featurizer.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
806
+ "vision_backbone.fused_featurizer.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
807
+ "vision_backbone.fused_featurizer.blocks.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
808
+ "vision_backbone.fused_featurizer.blocks.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
809
+ "vision_backbone.fused_featurizer.blocks.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
810
+ "vision_backbone.fused_featurizer.blocks.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
811
+ "vision_backbone.fused_featurizer.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
812
+ "vision_backbone.fused_featurizer.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
813
+ "vision_backbone.fused_featurizer.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
814
+ "vision_backbone.fused_featurizer.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
815
+ "vision_backbone.fused_featurizer.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
816
+ "vision_backbone.fused_featurizer.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
817
+ "vision_backbone.fused_featurizer.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
818
+ "vision_backbone.fused_featurizer.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
819
+ "vision_backbone.fused_featurizer.blocks.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
820
+ "vision_backbone.fused_featurizer.blocks.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
821
+ "vision_backbone.fused_featurizer.blocks.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
822
+ "vision_backbone.fused_featurizer.blocks.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
823
+ "vision_backbone.fused_featurizer.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
824
+ "vision_backbone.fused_featurizer.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
825
+ "vision_backbone.fused_featurizer.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
826
+ "vision_backbone.fused_featurizer.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
827
+ "vision_backbone.fused_featurizer.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
828
+ "vision_backbone.fused_featurizer.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
829
+ "vision_backbone.fused_featurizer.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
830
+ "vision_backbone.fused_featurizer.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
831
+ "vision_backbone.fused_featurizer.blocks.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
832
+ "vision_backbone.fused_featurizer.blocks.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
833
+ "vision_backbone.fused_featurizer.blocks.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
834
+ "vision_backbone.fused_featurizer.blocks.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
835
+ "vision_backbone.fused_featurizer.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
836
+ "vision_backbone.fused_featurizer.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
837
+ "vision_backbone.fused_featurizer.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
838
+ "vision_backbone.fused_featurizer.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
839
+ "vision_backbone.fused_featurizer.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
840
+ "vision_backbone.fused_featurizer.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
841
+ "vision_backbone.fused_featurizer.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
842
+ "vision_backbone.fused_featurizer.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
843
+ "vision_backbone.fused_featurizer.blocks.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
844
+ "vision_backbone.fused_featurizer.blocks.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
845
+ "vision_backbone.fused_featurizer.blocks.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
846
+ "vision_backbone.fused_featurizer.blocks.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
847
+ "vision_backbone.fused_featurizer.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
848
+ "vision_backbone.fused_featurizer.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
849
+ "vision_backbone.fused_featurizer.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
850
+ "vision_backbone.fused_featurizer.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
851
+ "vision_backbone.fused_featurizer.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
852
+ "vision_backbone.fused_featurizer.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
853
+ "vision_backbone.fused_featurizer.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
854
+ "vision_backbone.fused_featurizer.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
855
+ "vision_backbone.fused_featurizer.blocks.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
856
+ "vision_backbone.fused_featurizer.blocks.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
857
+ "vision_backbone.fused_featurizer.blocks.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
858
+ "vision_backbone.fused_featurizer.blocks.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
859
+ "vision_backbone.fused_featurizer.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
860
+ "vision_backbone.fused_featurizer.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
861
+ "vision_backbone.fused_featurizer.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
862
+ "vision_backbone.fused_featurizer.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
863
+ "vision_backbone.fused_featurizer.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
864
+ "vision_backbone.fused_featurizer.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
865
+ "vision_backbone.fused_featurizer.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
866
+ "vision_backbone.fused_featurizer.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
867
+ "vision_backbone.fused_featurizer.blocks.24.mlp.fc1.bias": "model-00001-of-00003.safetensors",
868
+ "vision_backbone.fused_featurizer.blocks.24.mlp.fc1.weight": "model-00001-of-00003.safetensors",
869
+ "vision_backbone.fused_featurizer.blocks.24.mlp.fc2.bias": "model-00001-of-00003.safetensors",
870
+ "vision_backbone.fused_featurizer.blocks.24.mlp.fc2.weight": "model-00001-of-00003.safetensors",
871
+ "vision_backbone.fused_featurizer.blocks.24.norm1.bias": "model-00001-of-00003.safetensors",
872
+ "vision_backbone.fused_featurizer.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
873
+ "vision_backbone.fused_featurizer.blocks.24.norm2.bias": "model-00001-of-00003.safetensors",
874
+ "vision_backbone.fused_featurizer.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
875
+ "vision_backbone.fused_featurizer.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
876
+ "vision_backbone.fused_featurizer.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
877
+ "vision_backbone.fused_featurizer.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
878
+ "vision_backbone.fused_featurizer.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
879
+ "vision_backbone.fused_featurizer.blocks.25.mlp.fc1.bias": "model-00001-of-00003.safetensors",
880
+ "vision_backbone.fused_featurizer.blocks.25.mlp.fc1.weight": "model-00001-of-00003.safetensors",
881
+ "vision_backbone.fused_featurizer.blocks.25.mlp.fc2.bias": "model-00001-of-00003.safetensors",
882
+ "vision_backbone.fused_featurizer.blocks.25.mlp.fc2.weight": "model-00001-of-00003.safetensors",
883
+ "vision_backbone.fused_featurizer.blocks.25.norm1.bias": "model-00001-of-00003.safetensors",
884
+ "vision_backbone.fused_featurizer.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
885
+ "vision_backbone.fused_featurizer.blocks.25.norm2.bias": "model-00001-of-00003.safetensors",
886
+ "vision_backbone.fused_featurizer.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
887
+ "vision_backbone.fused_featurizer.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
888
+ "vision_backbone.fused_featurizer.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
889
+ "vision_backbone.fused_featurizer.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
890
+ "vision_backbone.fused_featurizer.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
891
+ "vision_backbone.fused_featurizer.blocks.26.mlp.fc1.bias": "model-00001-of-00003.safetensors",
892
+ "vision_backbone.fused_featurizer.blocks.26.mlp.fc1.weight": "model-00001-of-00003.safetensors",
893
+ "vision_backbone.fused_featurizer.blocks.26.mlp.fc2.bias": "model-00001-of-00003.safetensors",
894
+ "vision_backbone.fused_featurizer.blocks.26.mlp.fc2.weight": "model-00001-of-00003.safetensors",
895
+ "vision_backbone.fused_featurizer.blocks.26.norm1.bias": "model-00001-of-00003.safetensors",
896
+ "vision_backbone.fused_featurizer.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
897
+ "vision_backbone.fused_featurizer.blocks.26.norm2.bias": "model-00001-of-00003.safetensors",
898
+ "vision_backbone.fused_featurizer.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
899
+ "vision_backbone.fused_featurizer.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
900
+ "vision_backbone.fused_featurizer.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
901
+ "vision_backbone.fused_featurizer.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
902
+ "vision_backbone.fused_featurizer.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
903
+ "vision_backbone.fused_featurizer.blocks.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
904
+ "vision_backbone.fused_featurizer.blocks.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
905
+ "vision_backbone.fused_featurizer.blocks.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
906
+ "vision_backbone.fused_featurizer.blocks.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
907
+ "vision_backbone.fused_featurizer.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
908
+ "vision_backbone.fused_featurizer.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
909
+ "vision_backbone.fused_featurizer.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
910
+ "vision_backbone.fused_featurizer.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
911
+ "vision_backbone.fused_featurizer.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
912
+ "vision_backbone.fused_featurizer.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
913
+ "vision_backbone.fused_featurizer.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
914
+ "vision_backbone.fused_featurizer.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
915
+ "vision_backbone.fused_featurizer.blocks.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
916
+ "vision_backbone.fused_featurizer.blocks.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
917
+ "vision_backbone.fused_featurizer.blocks.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
918
+ "vision_backbone.fused_featurizer.blocks.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
919
+ "vision_backbone.fused_featurizer.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
920
+ "vision_backbone.fused_featurizer.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
921
+ "vision_backbone.fused_featurizer.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
922
+ "vision_backbone.fused_featurizer.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
923
+ "vision_backbone.fused_featurizer.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
924
+ "vision_backbone.fused_featurizer.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
925
+ "vision_backbone.fused_featurizer.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
926
+ "vision_backbone.fused_featurizer.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
927
+ "vision_backbone.fused_featurizer.blocks.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
928
+ "vision_backbone.fused_featurizer.blocks.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
929
+ "vision_backbone.fused_featurizer.blocks.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
930
+ "vision_backbone.fused_featurizer.blocks.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
931
+ "vision_backbone.fused_featurizer.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
932
+ "vision_backbone.fused_featurizer.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
933
+ "vision_backbone.fused_featurizer.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
934
+ "vision_backbone.fused_featurizer.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
935
+ "vision_backbone.fused_featurizer.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
936
+ "vision_backbone.fused_featurizer.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
937
+ "vision_backbone.fused_featurizer.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
938
+ "vision_backbone.fused_featurizer.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
939
+ "vision_backbone.fused_featurizer.blocks.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
940
+ "vision_backbone.fused_featurizer.blocks.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
941
+ "vision_backbone.fused_featurizer.blocks.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
942
+ "vision_backbone.fused_featurizer.blocks.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
943
+ "vision_backbone.fused_featurizer.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
944
+ "vision_backbone.fused_featurizer.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
945
+ "vision_backbone.fused_featurizer.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
946
+ "vision_backbone.fused_featurizer.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
947
+ "vision_backbone.fused_featurizer.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
948
+ "vision_backbone.fused_featurizer.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
949
+ "vision_backbone.fused_featurizer.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
950
+ "vision_backbone.fused_featurizer.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
951
+ "vision_backbone.fused_featurizer.blocks.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
952
+ "vision_backbone.fused_featurizer.blocks.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
953
+ "vision_backbone.fused_featurizer.blocks.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
954
+ "vision_backbone.fused_featurizer.blocks.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
955
+ "vision_backbone.fused_featurizer.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
956
+ "vision_backbone.fused_featurizer.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
957
+ "vision_backbone.fused_featurizer.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
958
+ "vision_backbone.fused_featurizer.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
959
+ "vision_backbone.fused_featurizer.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
960
+ "vision_backbone.fused_featurizer.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
961
+ "vision_backbone.fused_featurizer.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
962
+ "vision_backbone.fused_featurizer.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
963
+ "vision_backbone.fused_featurizer.blocks.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
964
+ "vision_backbone.fused_featurizer.blocks.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
965
+ "vision_backbone.fused_featurizer.blocks.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
966
+ "vision_backbone.fused_featurizer.blocks.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
967
+ "vision_backbone.fused_featurizer.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
968
+ "vision_backbone.fused_featurizer.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
969
+ "vision_backbone.fused_featurizer.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
970
+ "vision_backbone.fused_featurizer.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
971
+ "vision_backbone.fused_featurizer.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
972
+ "vision_backbone.fused_featurizer.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
973
+ "vision_backbone.fused_featurizer.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
974
+ "vision_backbone.fused_featurizer.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
975
+ "vision_backbone.fused_featurizer.blocks.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
976
+ "vision_backbone.fused_featurizer.blocks.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
977
+ "vision_backbone.fused_featurizer.blocks.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
978
+ "vision_backbone.fused_featurizer.blocks.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
979
+ "vision_backbone.fused_featurizer.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
980
+ "vision_backbone.fused_featurizer.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
981
+ "vision_backbone.fused_featurizer.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
982
+ "vision_backbone.fused_featurizer.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
983
+ "vision_backbone.fused_featurizer.norm.bias": "model-00001-of-00003.safetensors",
984
+ "vision_backbone.fused_featurizer.norm.weight": "model-00001-of-00003.safetensors",
985
+ "vision_backbone.fused_featurizer.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
986
+ "vision_backbone.fused_featurizer.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
987
+ "vision_backbone.fused_featurizer.pos_embed": "model-00001-of-00003.safetensors"
988
+ }
989
+ }
modeling_prismatic.py ADDED
@@ -0,0 +1,561 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ modeling_prismatic.py
3
+
4
+ Core HuggingFace-style PrismaticPreTrainedModel and PrismaticForConditionalGeneration class definitions, inheriting
5
+ from the default `transformers.PretrainedModel`. Meant to be standalone and self-contained, but exactly replicate the
6
+ logic in `prismatic.models.vlms.prismatic.py`.
7
+
8
+ Note =>> for the time being, not adding the custom HF "docstring" formatting.
9
+
10
+ References [LLaVa, IDEFICS-2]:
11
+ => https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava/modeling_llava.py
12
+ => https://github.com/huggingface/transformers/blob/main/src/transformers/models/idefics2/modeling_idefics2.py
13
+ """
14
+
15
+ import logging
16
+ from dataclasses import dataclass
17
+ from functools import partial
18
+ from typing import Any, Callable, ClassVar, Dict, List, Optional, Tuple, Union
19
+
20
+ import numpy as np
21
+ import timm
22
+ import tokenizers
23
+ import torch
24
+ import torch.nn as nn
25
+ import transformers
26
+ from timm.models.vision_transformer import LayerScale
27
+ from transformers import AutoModelForCausalLM, PretrainedConfig, PreTrainedModel
28
+ from transformers.modeling_outputs import ModelOutput
29
+
30
+ from .configuration_prismatic import OpenVLAConfig, PrismaticConfig
31
+
32
+ # Get Logger
33
+ logger = logging.getLogger(__name__)
34
+
35
+
36
+ # === PyTorch/HuggingFace Default IGNORE_INDEX (for CrossEntropyLoss labels)
37
+ IGNORE_INDEX = -100
38
+
39
+
40
+ # === Utility Functions for Monkey-Patching ===
41
+ def unpack_tuple(fn: Callable[[Any], Tuple[Any]]) -> Callable[[Any], Any]:
42
+ def wrapper(*args: Any, **kwargs: Any) -> Any:
43
+ result = fn(*args, **kwargs)
44
+ return result[0] if isinstance(result, tuple) else result
45
+
46
+ return wrapper
47
+
48
+
49
+ # HF Transformers overwrites parameters with names containing `gamma`; we're going to patch VisionBackbone.LayerScale.
50
+ # =>> TIMM :: https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/vision_transformer.py#L109
51
+ # =>> Transformers :: https://github.com/huggingface/transformers/blob/main/src/transformers/modeling_utils.py#L3960
52
+ def _ls_new_forward(self, x: torch.Tensor) -> torch.Tensor:
53
+ return x.mul_(self.scale_factor) if self.inplace else x * self.scale_factor
54
+
55
+
56
+ def ls_apply_patch(ls_module: LayerScale):
57
+ ls_module.scale_factor = nn.Parameter(ls_module.gamma.clone())
58
+ ls_module.forward = _ls_new_forward.__get__(ls_module, LayerScale)
59
+ del ls_module.gamma
60
+
61
+
62
+ # === Prismatic Vision Backbone (nn.Module) Definitions (w/ Fused Backbone Support) ===
63
+ class PrismaticVisionBackbone(nn.Module):
64
+ def __init__(
65
+ self,
66
+ use_fused_vision_backbone: bool,
67
+ image_sizes: List[int],
68
+ timm_model_ids: List[str],
69
+ timm_override_act_layers: List[Optional[str]],
70
+ ) -> None:
71
+ super().__init__()
72
+ self.use_fused_vision_backbone = use_fused_vision_backbone
73
+
74
+ # [Contract] Validate number of (fused) vision backbones, create "alpha" featurizer and Instantiate
75
+ # =>> Note :: Monkey-Patch the `forward()` function of the backbone to ensure FSDP-compatibility
76
+ # Hardcodes `get_intermediate_layers` to return the **SECOND-TO-LAST** layer patches!
77
+ assert len(timm_model_ids) <= 2, "Prismatic models only support up to 2 (fused) vision backbones!"
78
+ self.featurizer = timm.create_model(
79
+ timm_model_ids[0],
80
+ pretrained=False,
81
+ num_classes=0,
82
+ img_size=image_sizes[0],
83
+ act_layer=timm_override_act_layers[0],
84
+ )
85
+ self.featurizer.forward = unpack_tuple(
86
+ partial(self.featurizer.get_intermediate_layers, n={len(self.featurizer.blocks) - 2})
87
+ )
88
+ self.embed_dim = self.featurizer.embed_dim
89
+
90
+ # If `use_fused_vision_backbone` =>> create "beta" featurizer
91
+ if self.use_fused_vision_backbone:
92
+ self.fused_featurizer = timm.create_model(
93
+ timm_model_ids[1],
94
+ pretrained=False,
95
+ num_classes=0,
96
+ img_size=image_sizes[1],
97
+ act_layer=timm_override_act_layers[1],
98
+ )
99
+ self.fused_featurizer.forward = unpack_tuple(
100
+ partial(self.fused_featurizer.get_intermediate_layers, n={len(self.fused_featurizer.blocks) - 2})
101
+ )
102
+ self.embed_dim += self.fused_featurizer.embed_dim
103
+
104
+ # Patch `vision_backbone.featurizer` and `vision_backbone.fused_featurizer` with HF-Compatible LayerScale
105
+ for module in self.featurizer.modules():
106
+ if isinstance(module, LayerScale):
107
+ ls_apply_patch(module)
108
+
109
+ if self.use_fused_vision_backbone:
110
+ for module in self.fused_featurizer.modules():
111
+ if isinstance(module, LayerScale):
112
+ ls_apply_patch(module)
113
+
114
+ def forward(self, pixel_values: torch.Tensor) -> torch.Tensor:
115
+ """Run image (`pixel_values`) through featurizer; if channel-stacked, then dispatch and sequence stack."""
116
+ if not self.use_fused_vision_backbone:
117
+ return self.featurizer(pixel_values)
118
+
119
+ # Split `pixel_values :: [bsz, 2 * 3, resolution, resolution]` =>> featurize =>> channel stack
120
+ img, img_fused = torch.split(pixel_values, [3, 3], dim=1)
121
+ patches, patches_fused = self.featurizer(img), self.fused_featurizer(img_fused)
122
+
123
+ return torch.cat([patches, patches_fused], dim=2)
124
+
125
+
126
+ # === Prismatic Projector (nn.Module) Definitions ===
127
+ class PrismaticProjector(nn.Module):
128
+ def __init__(self, use_fused_vision_backbone: bool, vision_dim: int, llm_dim: int) -> None:
129
+ super().__init__()
130
+ self.use_fused_vision_backbone = use_fused_vision_backbone
131
+ self.vision_dim, self.llm_dim = vision_dim, llm_dim
132
+
133
+ # Switch on `use_fused_vision_backbone` =>> use slightly different MLPs and projection factors!
134
+ if not self.use_fused_vision_backbone:
135
+ self.fc1 = nn.Linear(self.vision_dim, self.llm_dim, bias=True)
136
+ self.fc2 = nn.Linear(self.llm_dim, self.llm_dim, bias=True)
137
+ self.act_fn1 = nn.GELU()
138
+ else:
139
+ initial_projection_dim = 4 * vision_dim
140
+ self.fc1 = nn.Linear(self.vision_dim, initial_projection_dim, bias=True)
141
+ self.fc2 = nn.Linear(initial_projection_dim, self.llm_dim, bias=True)
142
+ self.fc3 = nn.Linear(self.llm_dim, self.llm_dim, bias=True)
143
+ self.act_fn1 = nn.GELU()
144
+ self.act_fn2 = nn.GELU()
145
+
146
+ def forward(self, img_patches: torch.Tensor) -> torch.Tensor:
147
+ if not self.use_fused_vision_backbone:
148
+ projected_features = self.fc1(img_patches)
149
+ projected_features = self.act_fn1(projected_features)
150
+ projected_features = self.fc2(projected_features)
151
+ else:
152
+ projected_features = self.fc1(img_patches)
153
+ projected_features = self.act_fn1(projected_features)
154
+ projected_features = self.fc2(projected_features)
155
+ projected_features = self.act_fn2(projected_features)
156
+ projected_features = self.fc3(projected_features)
157
+
158
+ return projected_features
159
+
160
+
161
+ # === Main HF Class Definitions ===
162
+ @dataclass
163
+ class PrismaticCausalLMOutputWithPast(ModelOutput):
164
+ """Base class for Prismatic casual (visually-conditioned) language model outputs; also exposes visual features."""
165
+
166
+ loss: Optional[torch.FloatTensor] = None
167
+ logits: torch.FloatTensor = None
168
+ past_key_values: Optional[Tuple[Tuple[torch.FloatTensor]]] = None
169
+ hidden_states: Optional[Tuple[torch.FloatTensor, ...]] = None
170
+ attentions: Optional[Tuple[torch.FloatTensor]] = None
171
+
172
+ # Additions for VLMs
173
+ projector_features: Optional[torch.FloatTensor] = None
174
+
175
+
176
+ class PrismaticPreTrainedModel(PreTrainedModel):
177
+ config_class: PretrainedConfig = PrismaticConfig
178
+ base_model_prefix: str = "model"
179
+ supports_gradient_checkpointing: bool = True
180
+
181
+ _no_split_modules: ClassVar[List[str]] = ["PrismaticProjector"]
182
+ _skip_keys_device_placement: str = "past_key_values"
183
+ _supports_flash_attn_2: bool = True
184
+
185
+ def _init_weights(self, module: nn.Module) -> None:
186
+ # Important :: this HF ported version is *not* meant for training from scratch; only inference and fine-tuning!
187
+ # => As such, this init_weights code is not correct; if training VLMs from scratch, use the main codebase at
188
+ # https://github.com/TRI-ML/prismatic-vlms
189
+ std = (
190
+ self.config.initializer_range
191
+ if hasattr(self.config, "initializer_range")
192
+ else self.config.text_config.initializer_range
193
+ )
194
+
195
+ if hasattr(module, "class_embedding"):
196
+ module.class_embedding.data.normal_(mean=0.0, std=std)
197
+
198
+ if isinstance(module, (nn.Linear, nn.Conv2d)):
199
+ module.weight.data.normal_(mean=0.0, std=std)
200
+ if module.bias is not None:
201
+ module.bias.data.zero_()
202
+ elif isinstance(module, nn.Embedding):
203
+ module.weight.data.normal_(mean=0.0, std=std)
204
+ if module.padding_idx is not None:
205
+ module.weight.data[module.padding_idx].zero_()
206
+
207
+ @property
208
+ def _supports_sdpa(self) -> bool:
209
+ """Check LLM supports SDPA Attention"""
210
+ return self.language_model._supports_sdpa
211
+
212
+
213
+ class PrismaticForConditionalGeneration(PrismaticPreTrainedModel):
214
+ def __init__(self, config: PrismaticConfig) -> None:
215
+ super().__init__(config)
216
+
217
+ # [Validation] Lightweight Validate on `config` Fields + Dependency Versions
218
+ if config.use_fused_vision_backbone is None:
219
+ raise ValueError("Missing config field `use_fused_vision_backbone`")
220
+
221
+ if timm.__version__ not in {"0.9.10", "0.9.11", "0.9.12", "0.9.16"}:
222
+ raise NotImplementedError(
223
+ "TIMM Version must be >= 0.9.10 and < 1.0.0 (breaking); please raise a GitHub Issue "
224
+ "if you urgently need support for latest TIMM versions."
225
+ )
226
+
227
+ if (transformers.__version__ != "4.40.1") or (tokenizers.__version__ != "0.19.1"):
228
+ logger.warning(
229
+ f"Expected `transformers==4.40.1` and `tokenizers==0.19.1` but got "
230
+ f"`transformers=={transformers.__version__}` and `tokenizers=={tokenizers.__version__}`; "
231
+ f"there might be inference-time regressions due to dependency changes. If in doubt, please"
232
+ f"use the above versions."
233
+ )
234
+
235
+ # Instantiate PrismaticVisionBackbone (w/ Potential Fused Backbone)
236
+ self.vision_backbone = PrismaticVisionBackbone(
237
+ config.use_fused_vision_backbone, config.image_sizes, config.timm_model_ids, config.timm_override_act_layers
238
+ )
239
+
240
+ # Create Multimodal Projector
241
+ self.projector = PrismaticProjector(
242
+ config.use_fused_vision_backbone,
243
+ vision_dim=self.vision_backbone.embed_dim,
244
+ llm_dim=config.text_config.hidden_size,
245
+ )
246
+
247
+ # Instantiate LLM Backbone
248
+ self.language_model = AutoModelForCausalLM.from_config(
249
+ config.text_config, attn_implementation=config._attn_implementation
250
+ )
251
+ self.vocab_size = config.text_config.vocab_size
252
+ self.pad_token_id = config.pad_token_id
253
+
254
+ # HF Boilerplate =>> initializes weights via `_init_weights()` and sets gradient checkpointing
255
+ self.post_init()
256
+
257
+ # === `PreTrainedModel` Boilerplate ===
258
+ def get_input_embeddings(self) -> nn.Module:
259
+ return self.language_model.get_input_embeddings()
260
+
261
+ def set_input_embeddings(self, value: nn.Module) -> None:
262
+ self.language_model.set_input_embeddings(value)
263
+
264
+ def get_output_embeddings(self) -> nn.Module:
265
+ return self.language_model.get_output_embeddings()
266
+
267
+ def set_output_embeddings(self, new_embeddings: nn.Module) -> None:
268
+ self.language_model.set_output_embeddings(new_embeddings)
269
+
270
+ def get_decoder(self) -> nn.Module:
271
+ return self.language_model.get_decoder()
272
+
273
+ def set_decoder(self, decoder: nn.Module) -> None:
274
+ self.language_model.set_decoder(decoder)
275
+
276
+ def tie_weights(self) -> None:
277
+ self.language_model.tie_weights() # Note: `Llama-2` and `Mistral` don't tie weights (no-op)
278
+
279
+ def resize_token_embeddings(
280
+ self, new_num_tokens: Optional[int] = None, pad_to_multiple_of: Optional[int] = None
281
+ ) -> nn.Embedding:
282
+ updated_embeddings = self.language_model.resize_token_embeddings(new_num_tokens, pad_to_multiple_of)
283
+
284
+ # Update config/instance variables
285
+ self.config.text_config.vocab_size = updated_embeddings.num_embeddings
286
+ self.vocab_size = updated_embeddings.num_embeddings
287
+
288
+ return updated_embeddings
289
+
290
+ # === Core Prismatic VLM `forward()` Logic ===
291
+ def forward(
292
+ self,
293
+ input_ids: Optional[torch.LongTensor] = None,
294
+ attention_mask: Optional[torch.Tensor] = None,
295
+ pixel_values: Optional[torch.FloatTensor] = None,
296
+ labels: Optional[torch.LongTensor] = None,
297
+ inputs_embeds: Optional[torch.FloatTensor] = None,
298
+ past_key_values: Optional[List[torch.FloatTensor]] = None,
299
+ use_cache: Optional[bool] = None,
300
+ output_attentions: Optional[bool] = None,
301
+ output_hidden_states: Optional[bool] = None,
302
+ output_projector_features: Optional[bool] = None,
303
+ return_dict: Optional[bool] = None,
304
+ ) -> Union[Tuple, PrismaticCausalLMOutputWithPast]:
305
+ """Run a forward pass through the VLM, returning a PrismaticCausalLMOutputWithPast instance."""
306
+ output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
307
+ output_hidden_states = (
308
+ output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
309
+ )
310
+ output_projector_features = output_projector_features if output_projector_features is not None else False
311
+ return_dict = return_dict if return_dict is not None else self.config.use_return_dict
312
+
313
+ # Respect `use_cache` only if not training (even if `gradient_checkpointing` is off)
314
+ use_cache = use_cache and not self.training
315
+
316
+ # Instantiate Placeholder for Projector Features
317
+ projected_patch_embeddings = None
318
+
319
+ # Note :: We only support forward passes with the following cases:
320
+ # => Cached Generation :: (input_ids.shape[1] == 1) and (past_key_values is not None)
321
+ # => Unimodal Forward :: (pixel_values is None)
322
+ # => Multimodal Forward :: (pixel_values is not None) and (input_ids/embeds.shape[0] == pixel_values.shape[0])
323
+
324
+ # === Handle Generation with Cache (`input_ids.shape[1] == 1`) =>> requires `past_keys_values` ===
325
+ if input_ids.shape[1] == 1:
326
+ assert input_ids.shape[0] == 1, "Generation is only currently supported for batch size of 1!"
327
+ assert past_key_values is not None, "You must provide `past_key_values` during cached generation!"
328
+ assert labels is None, "Unexpected key `labels` provided during cached generation!"
329
+
330
+ language_model_output = self.language_model(
331
+ input_ids=input_ids,
332
+ attention_mask=None,
333
+ position_ids=None,
334
+ past_key_values=past_key_values,
335
+ inputs_embeds=None,
336
+ labels=None,
337
+ use_cache=use_cache,
338
+ output_attentions=output_attentions,
339
+ output_hidden_states=output_hidden_states,
340
+ return_dict=return_dict,
341
+ )
342
+
343
+ # === Handle Unimodal Forward ===
344
+ elif pixel_values is None:
345
+ assert (input_ids is not None) and (inputs_embeds is None), "Missing `input_ids` in language-only forward!"
346
+ assert past_key_values is None, "Unexpected key `past_key_values` provided during language-only forward!"
347
+
348
+ language_model_output = self.language_model(
349
+ input_ids=input_ids,
350
+ attention_mask=attention_mask,
351
+ position_ids=None,
352
+ past_key_values=None,
353
+ inputs_embeds=None,
354
+ labels=labels,
355
+ use_cache=use_cache,
356
+ output_attentions=output_attentions,
357
+ output_hidden_states=output_hidden_states,
358
+ return_dict=return_dict,
359
+ )
360
+
361
+ # === Handle Multimodal Forward ===
362
+ elif (input_ids.shape[0] == pixel_values.shape[0]) or (inputs_embeds.shape[0] == pixel_values.shape[0]):
363
+ assert past_key_values is None, "Unexpected key `past_key_values` provided during language-only forward!"
364
+
365
+ # Visual Feature Extraction
366
+ patch_features = self.vision_backbone(pixel_values)
367
+
368
+ # Projection Logic =>> Update Attention Mask
369
+ projected_patch_embeddings = self.projector(patch_features)
370
+ projected_patch_attention_mask = None
371
+ if attention_mask is not None:
372
+ projected_patch_attention_mask = torch.full(
373
+ (projected_patch_embeddings.shape[0], projected_patch_embeddings.shape[1]),
374
+ fill_value=True,
375
+ dtype=attention_mask.dtype,
376
+ device=attention_mask.device,
377
+ )
378
+
379
+ # Get Input Embeddings (from Language Model Embeddings)
380
+ input_embeddings = self.get_input_embeddings()(input_ids)
381
+
382
+ # Build Multimodal Embeddings & Attention Mask =>> Prismatic defaults to inserting after <BOS> token (1:)
383
+ multimodal_embeddings = torch.cat(
384
+ [input_embeddings[:, :1, :], projected_patch_embeddings, input_embeddings[:, 1:, :]], dim=1
385
+ )
386
+ multimodal_attention_mask = None
387
+ if attention_mask is not None:
388
+ multimodal_attention_mask = torch.cat(
389
+ [attention_mask[:, :1], projected_patch_attention_mask, attention_mask[:, 1:]], dim=1
390
+ )
391
+
392
+ # Build Labels (if specified) =>> Ignore Labels for Patch Embeddings
393
+ multimodal_labels = None
394
+ if labels is not None:
395
+ projected_patch_labels = torch.full(
396
+ (projected_patch_embeddings.shape[0], projected_patch_embeddings.shape[1]),
397
+ fill_value=IGNORE_INDEX,
398
+ dtype=labels.dtype,
399
+ device=labels.device,
400
+ )
401
+ multimodal_labels = torch.cat([labels[:, :1], projected_patch_labels, labels[:, 1:]], dim=1)
402
+
403
+ # Dispatch to Language Model
404
+ language_model_output = self.language_model(
405
+ input_ids=None,
406
+ attention_mask=multimodal_attention_mask,
407
+ position_ids=None,
408
+ past_key_values=None,
409
+ inputs_embeds=multimodal_embeddings,
410
+ labels=multimodal_labels,
411
+ use_cache=use_cache,
412
+ output_attentions=output_attentions,
413
+ output_hidden_states=output_hidden_states,
414
+ return_dict=return_dict,
415
+ )
416
+
417
+ # === Otherwise =>> Assume Invalid! ===
418
+ elif (input_ids.shape[0] != pixel_values.shape[0]) or (inputs_embeds.shape[0] != pixel_values.shape[0]):
419
+ raise ValueError("Non-homogenous batch of (text, image) input -- forward() does not support mixed batches!")
420
+
421
+ else:
422
+ raise ValueError(
423
+ "Invalid PrismaticForConditionalGeneration `forward()` call with provided arguments:\n"
424
+ f"=> `input_ids` = {input_ids is not None}\n"
425
+ f"=> `attention_mask` = {attention_mask is not None}\n"
426
+ f"=> `pixel_values` = {pixel_values is not None}\n"
427
+ f"=> `labels` = {labels is not None}\n"
428
+ f"=> `input_embeds` = {inputs_embeds is not None}\n"
429
+ f"=> `past_key_values` = {past_key_values is not None}\n"
430
+ f"=> `use_cache` = {use_cache}"
431
+ )
432
+
433
+ # Unpack `language_model_output` and return PrismaticCausalLMOutputWithPast (or tuple if not `return_dict`)
434
+ if not return_dict:
435
+ if output_projector_features and (projected_patch_embeddings is not None):
436
+ return *language_model_output, projected_patch_embeddings
437
+
438
+ return language_model_output
439
+
440
+ return PrismaticCausalLMOutputWithPast(
441
+ loss=language_model_output.loss,
442
+ logits=language_model_output.logits,
443
+ past_key_values=language_model_output.past_key_values,
444
+ hidden_states=language_model_output.hidden_states,
445
+ attentions=language_model_output.attentions,
446
+ projector_features=projected_patch_embeddings,
447
+ )
448
+
449
+ # === GenerationMixin Methods ===
450
+ def prepare_inputs_for_generation(
451
+ self,
452
+ input_ids: Optional[torch.Tensor] = None,
453
+ past_key_values: Optional[List[torch.FloatTensor]] = None,
454
+ inputs_embeds: Optional[torch.FloatTensor] = None,
455
+ pixel_values: Optional[torch.FloatTensor] = None,
456
+ attention_mask: Optional[torch.Tensor] = None,
457
+ **kwargs: str,
458
+ ) -> Dict[str, torch.Tensor]:
459
+ """Borrowed from `LlamaForCausalLM` and simplified for batch size = 1; mirrors original PrismaticVLM logic."""
460
+ if ((input_ids is not None) and (input_ids.shape[0] > 1)) or (
461
+ (inputs_embeds is not None) and (inputs_embeds.shape[0] > 1)
462
+ ):
463
+ raise ValueError("Generation with batch size > 1 is not currently supported!")
464
+
465
+ # Handle `past_key_values` (cache) =>> assume `input_ids` just has unprocessed tokens
466
+ if past_key_values is not None:
467
+ input_ids = input_ids[:, -1:]
468
+
469
+ # If `input_embeds` are passed, we only want to use them in the 1st generation step
470
+ if inputs_embeds is not None and past_key_values is None:
471
+ model_inputs = {"input_embeds": inputs_embeds}
472
+ else:
473
+ model_inputs = {"input_ids": input_ids}
474
+
475
+ # Make sure `pixel_values` are preserved in `model_inputs`
476
+ model_inputs.update(
477
+ {
478
+ "attention_mask": attention_mask,
479
+ "pixel_values": pixel_values,
480
+ "past_key_values": past_key_values,
481
+ "use_cache": kwargs.get("use_cache"),
482
+ }
483
+ )
484
+
485
+ return model_inputs
486
+
487
+ # Defer to Language Model (all handle this differently, with different return types)
488
+ def _reorder_cache(self, *args, **kwargs) -> Any:
489
+ return self.language_model._reorder_cache(*args, **kwargs)
490
+
491
+
492
+ class OpenVLAForActionPrediction(PrismaticForConditionalGeneration):
493
+ config_class: PretrainedConfig = OpenVLAConfig
494
+
495
+ def __init__(self, config: OpenVLAConfig) -> None:
496
+ super().__init__(config)
497
+ self.norm_stats = config.norm_stats
498
+
499
+ # Compute action bins
500
+ self.bins = np.linspace(-1, 1, config.n_action_bins)
501
+ self.bin_centers = (self.bins[:-1] + self.bins[1:]) / 2.0
502
+
503
+ # Compute vocab size for de-tokenization -- revert added "multiple of"
504
+ self.vocab_size = self.config.text_config.vocab_size - self.config.pad_to_multiple_of
505
+
506
+ def predict_action(
507
+ self, input_ids: Optional[torch.LongTensor] = None, unnorm_key: Optional[str] = None, **kwargs
508
+ ) -> np.ndarray:
509
+ """Thin wrapper around .generate() that decodes predicted actions and unnormalizes them."""
510
+ # We need to add this special empty token ('') after the colon (':') token in "ASSISTANT:"
511
+ # in order for the predictions to match the training configuration and be accurate.
512
+ input_ids = torch.cat(
513
+ (input_ids, torch.unsqueeze(torch.Tensor([29871]).long(), dim=0).to(input_ids.device)), dim=1
514
+ )
515
+
516
+ # Run VLA inference
517
+ generated_ids = self.generate(input_ids, max_new_tokens=self.get_action_dim(unnorm_key), **kwargs)
518
+
519
+ # Extract predicted action tokens and translate into (normalized) continuous actions
520
+ predicted_action_token_ids = generated_ids[0, -self.get_action_dim(unnorm_key) :].cpu().numpy()
521
+ discretized_actions = self.vocab_size - predicted_action_token_ids
522
+ discretized_actions = np.clip(discretized_actions - 1, a_min=0, a_max=self.bin_centers.shape[0] - 1)
523
+ normalized_actions = self.bin_centers[discretized_actions]
524
+
525
+ # Unnormalize actions
526
+ action_norm_stats = self.get_action_stats(unnorm_key)
527
+ mask = action_norm_stats.get("mask", np.ones_like(action_norm_stats["q01"], dtype=bool))
528
+ action_high, action_low = np.array(action_norm_stats["q99"]), np.array(action_norm_stats["q01"])
529
+ actions = np.where(
530
+ mask,
531
+ 0.5 * (normalized_actions + 1) * (action_high - action_low) + action_low,
532
+ normalized_actions,
533
+ )
534
+
535
+ return actions
536
+
537
+ @staticmethod
538
+ def _check_unnorm_key(norm_stats, unnorm_key):
539
+ if unnorm_key is None:
540
+ assert len(norm_stats) == 1, (
541
+ f"Your model was trained on more than one dataset, "
542
+ f"please pass a `unnorm_key` from the following options to choose the statistics "
543
+ f"used for un-normalizing actions: {norm_stats.keys()}"
544
+ )
545
+ unnorm_key = next(iter(norm_stats.keys()))
546
+
547
+ assert unnorm_key in norm_stats, (
548
+ f"The `unnorm_key` you chose is not in the set of available dataset statistics, "
549
+ f"please choose from: {norm_stats.keys()}"
550
+ )
551
+ return unnorm_key
552
+
553
+ def get_action_dim(self, unnorm_key=None):
554
+ """Dimensionality of the policy's action space."""
555
+ unnorm_key = self._check_unnorm_key(self.norm_stats, unnorm_key)
556
+ return len(self.norm_stats[unnorm_key]["action"]["q01"])
557
+
558
+ def get_action_stats(self, unnorm_key=None):
559
+ """Dimensionality of the policy's action space."""
560
+ unnorm_key = self._check_unnorm_key(self.norm_stats, unnorm_key)
561
+ return self.norm_stats[unnorm_key]["action"]