config.json
3.4 KB · 170 lines · json Raw
1 {
2 "_name_or_path": "/mnt/public/mjwei/download_models/openvla/openvla-7b",
3 "arch_specifier": "no-align+fused-gelu-mlp",
4 "architectures": [
5 "OpenVLAForActionPrediction"
6 ],
7 "auto_map": {
8 "AutoConfig": "configuration_prismatic.OpenVLAConfig",
9 "AutoModelForVision2Seq": "modeling_prismatic.OpenVLAForActionPrediction"
10 },
11 "hf_llm_id": "meta-llama/Llama-2-7b-hf",
12 "image_resize_strategy": "resize-naive",
13 "image_sizes": [
14 224,
15 224
16 ],
17 "llm_backbone_id": "llama2-7b-pure",
18 "llm_max_length": 2048,
19 "model_type": "openvla",
20 "n_action_bins": 256,
21 "norm_stats": {
22 "libero_10": {
23 "action": {
24 "mask": [
25 true,
26 true,
27 true,
28 true,
29 true,
30 true,
31 false
32 ],
33 "max": [
34 0.9375,
35 0.9375,
36 0.9375,
37 0.30000001192092896,
38 0.29357144236564636,
39 0.375,
40 1.0
41 ],
42 "mean": [
43 0.01820324920117855,
44 0.05858374014496803,
45 -0.05592384561896324,
46 0.004626928828656673,
47 0.00289608770981431,
48 -0.007673131301999092,
49 0.5457824468612671
50 ],
51 "min": [
52 -0.9375,
53 -0.9375,
54 -0.9375,
55 -0.23642857372760773,
56 -0.3053571283817291,
57 -0.3675000071525574,
58 0.0
59 ],
60 "q01": [
61 -0.6348214149475098,
62 -0.7741071581840515,
63 -0.7633928656578064,
64 -0.09749999642372131,
65 -0.14819999992847435,
66 -0.2742857038974762,
67 0.0
68 ],
69 "q99": [
70 0.7714285850524902,
71 0.8464285731315613,
72 0.9375,
73 0.13928571343421936,
74 0.15964286029338837,
75 0.3246428668498993,
76 1.0
77 ],
78 "std": [
79 0.2825464606285095,
80 0.35904666781425476,
81 0.3673802614212036,
82 0.03770702704787254,
83 0.05429719388484955,
84 0.08725254982709885,
85 0.49815231561660767
86 ]
87 },
88 "num_trajectories": 379,
89 "num_transitions": 101469,
90 "proprio": {
91 "max": [
92 0.0,
93 0.0,
94 0.0,
95 0.0,
96 0.0,
97 0.0,
98 0.0
99 ],
100 "mean": [
101 0.0,
102 0.0,
103 0.0,
104 0.0,
105 0.0,
106 0.0,
107 0.0
108 ],
109 "min": [
110 0.0,
111 0.0,
112 0.0,
113 0.0,
114 0.0,
115 0.0,
116 0.0
117 ],
118 "q01": [
119 0.0,
120 0.0,
121 0.0,
122 0.0,
123 0.0,
124 0.0,
125 0.0
126 ],
127 "q99": [
128 0.0,
129 0.0,
130 0.0,
131 0.0,
132 0.0,
133 0.0,
134 0.0
135 ],
136 "std": [
137 0.0,
138 0.0,
139 0.0,
140 0.0,
141 0.0,
142 0.0,
143 0.0
144 ]
145 }
146 }
147 },
148 "output_projector_states": false,
149 "pad_to_multiple_of": 64,
150 "pad_token_id": 32000,
151 "text_config": {
152 "model_type": "llama",
153 "pad_token_id": 32000,
154 "torch_dtype": "bfloat16",
155 "vocab_size": 32064
156 },
157 "timm_model_ids": [
158 "vit_large_patch14_reg4_dinov2.lvd142m",
159 "vit_so400m_patch14_siglip_224"
160 ],
161 "timm_override_act_layers": [
162 null,
163 null
164 ],
165 "torch_dtype": "bfloat16",
166 "transformers_version": "4.40.1",
167 "use_fused_vision_backbone": true,
168 "vision_backbone_id": "dinosiglip-vit-so-224px"
169 }
170