Robotics
LeRobot
Safetensors
vision-language-action
eo1
File size: 8,253 Bytes
b9fde2e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
{
    "type": "eo1",
    "n_obs_steps": 1,
    "input_features": {
        "observation.state": {
            "type": "STATE",
            "shape": [
                6
            ]
        },
        "observation.images.front": {
            "type": "VISUAL",
            "shape": [
                3,
                480,
                640
            ]
        },
        "observation.images.arm": {
            "type": "VISUAL",
            "shape": [
                3,
                480,
                640
            ]
        }
    },
    "output_features": {
        "action": {
            "type": "ACTION",
            "shape": [
                6
            ]
        }
    },
    "device": "cuda",
    "use_amp": false,
    "use_peft": false,
    "push_to_hub": true,
    "repo_id": "Grigorij/PaP_objects_2_eo-1",
    "private": null,
    "tags": [
        "eo1",
        "robotics",
        "vision-language-action",
        "lerobot"
    ],
    "license": "mit",
    "pretrained_path": "lerobot/eo1-base",
    "pretrained_revision": null,
    "vlm_base": "lerobot/eo1-base",
    "vlm_config": {
        "_name_or_path": "",
        "action_pass_id": 151672,
        "action_token_id": 151666,
        "architectures": [
            "Qwen2_5_VLForConditionalGeneration"
        ],
        "chunk_size_feed_forward": 0,
        "dtype": "bfloat16",
        "eos_token_id": 151645,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "image_token_id": 151655,
        "is_encoder_decoder": false,
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "model_type": "qwen2_5_vl",
        "output_attentions": false,
        "output_hidden_states": false,
        "pad_token_id": 151643,
        "problem_type": null,
        "return_dict": true,
        "state_token_id": 151669,
        "text_config": {
            "_name_or_path": "",
            "architectures": null,
            "attention_dropout": 0.0,
            "bos_token_id": 151643,
            "chunk_size_feed_forward": 0,
            "dtype": "bfloat16",
            "eos_token_id": 151645,
            "hidden_act": "silu",
            "hidden_size": 2048,
            "id2label": {
                "0": "LABEL_0",
                "1": "LABEL_1"
            },
            "initializer_range": 0.02,
            "intermediate_size": 11008,
            "is_encoder_decoder": false,
            "label2id": {
                "LABEL_0": 0,
                "LABEL_1": 1
            },
            "layer_types": [
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention",
                "full_attention"
            ],
            "max_position_embeddings": 128000,
            "max_window_layers": 70,
            "model_type": "qwen2_5_vl_text",
            "num_attention_heads": 16,
            "num_hidden_layers": 36,
            "num_key_value_heads": 2,
            "output_attentions": false,
            "output_hidden_states": false,
            "pad_token_id": null,
            "problem_type": null,
            "return_dict": true,
            "rms_norm_eps": 1e-06,
            "rope_parameters": {
                "mrope_section": [
                    16,
                    24,
                    24
                ],
                "rope_theta": 1000000.0,
                "rope_type": "default",
                "type": "mrope"
            },
            "sliding_window": null,
            "use_cache": true,
            "use_sliding_window": false,
            "vocab_size": 151936
        },
        "tie_word_embeddings": true,
        "transformers_version": "5.5.4",
        "use_cache": false,
        "video_token_id": 151656,
        "vision_config": {
            "_name_or_path": "",
            "architectures": null,
            "chunk_size_feed_forward": 0,
            "depth": 32,
            "dtype": null,
            "fullatt_block_indexes": [
                7,
                15,
                23,
                31
            ],
            "hidden_act": "silu",
            "hidden_size": 1280,
            "id2label": {
                "0": "LABEL_0",
                "1": "LABEL_1"
            },
            "in_channels": 3,
            "in_chans": 3,
            "initializer_range": 0.02,
            "intermediate_size": 3420,
            "is_encoder_decoder": false,
            "label2id": {
                "LABEL_0": 0,
                "LABEL_1": 1
            },
            "model_type": "qwen2_5_vl",
            "num_heads": 16,
            "out_hidden_size": 2048,
            "output_attentions": false,
            "output_hidden_states": false,
            "patch_size": 14,
            "problem_type": null,
            "return_dict": true,
            "spatial_merge_size": 2,
            "spatial_patch_size": 14,
            "temporal_patch_size": 2,
            "tokens_per_second": 2,
            "window_size": 112
        },
        "vision_end_token_id": 151653,
        "vision_start_token_id": 151652,
        "vision_token_id": 151654,
        "vocab_size": 151936
    },
    "image_min_pixels": 50176,
    "image_max_pixels": 100352,
    "use_fast_processor": true,
    "chunk_size": 16,
    "n_action_steps": 16,
    "max_state_dim": 32,
    "max_action_dim": 32,
    "freeze_vision_tower": true,
    "freeze_llm": false,
    "flow_loss_weight": 1.0,
    "text_loss_weight": 0.01,
    "use_language_recipe": false,
    "recipe": {
        "messages": [
            {
                "role": "user",
                "content": "${task}\nPredict the next action in language.",
                "stream": "low_level",
                "target": false,
                "if_present": null,
                "tool_calls_from": null
            },
            {
                "role": "assistant",
                "content": "${subtask}",
                "stream": "low_level",
                "target": true,
                "if_present": "subtask",
                "tool_calls_from": null
            }
        ],
        "bindings": null,
        "blend": null,
        "weight": null,
        "route": null
    },
    "recipe_path": null,
    "tokenizer_max_length": 1000,
    "num_denoise_steps": 10,
    "num_action_layers": 2,
    "action_act": "linear",
    "time_sampling_beta_alpha": 1.5,
    "time_sampling_beta_beta": 1.0,
    "time_sampling_scale": 0.999,
    "time_sampling_offset": 0.001,
    "min_period": 0.004,
    "max_period": 4.0,
    "supervise_padding_action_dims": false,
    "supervise_padding_actions": true,
    "dtype": "bfloat16",
    "force_fp32_autocast": true,
    "attn_implementation": "sdpa",
    "gradient_checkpointing": false,
    "normalization_mapping": {
        "ACTION": "MEAN_STD",
        "STATE": "MEAN_STD",
        "VISUAL": "IDENTITY"
    },
    "optimizer_lr": 0.0001,
    "optimizer_betas": [
        0.9,
        0.999
    ],
    "optimizer_eps": 1e-08,
    "optimizer_weight_decay": 0.1,
    "optimizer_grad_clip_norm": 1.0,
    "scheduler_warmup_steps": 900,
    "scheduler_decay_steps": 30000,
    "scheduler_decay_lr": 0.0
}