RJK commited on
Commit
40e19c8
·
verified ·
1 Parent(s): 6259312

Add SmolVLA RoboCasa frozen-VLM checkpoint

Browse files
Files changed (17) hide show
  1. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/checkpoints/step-100000-epoch-04-loss=0.0626.safetensors +3 -0
  2. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/config.json +455 -0
  3. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/config.yaml +363 -0
  4. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/dataset_statistics.json +276 -0
  5. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/added_tokens.json +130 -0
  6. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/chat_template.json +3 -0
  7. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/chat_template.json.metadata +3 -0
  8. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/merges.txt +0 -0
  9. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/merges.txt.metadata +3 -0
  10. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/special_tokens_map.json +39 -0
  11. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/tokenizer.json +0 -0
  12. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/tokenizer.json.metadata +3 -0
  13. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/tokenizer_config.json +1192 -0
  14. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/tokenizer_config.json.metadata +3 -0
  15. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/vocab.json +0 -0
  16. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/vocab.json.metadata +3 -0
  17. smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/vlm_backbone_config.json +28 -0
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/checkpoints/step-100000-epoch-04-loss=0.0626.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60fd6271b46ce402921997c3bd2dc1ca360c749b42ecabe4a293f4ff7cbc4cdd
3
+ size 805540592
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/config.json ADDED
@@ -0,0 +1,455 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_ACTION_DIM": 29,
3
+ "_ACTION_HORIZON": 50,
4
+ "_CKPT_ROOT": "./checkpoints",
5
+ "_DEFAULT_ROBOCASA_DATA_ROOT": "./datasets/robocasa_lerobot_V2.1",
6
+ "_IMAGE_SIZE": 512,
7
+ "_LOCAL_ROBOCASA_DATA_ROOT": "./datasets/robocasa_lerobot_V2.1",
8
+ "_MAX_ACTION_DIM": 32,
9
+ "_MAX_STATE_DIM": 32,
10
+ "_MAX_STEPS": 100000,
11
+ "_PER_DEVICE_BATCH_SIZE": 64,
12
+ "_ROBOCASA_DATA_ROOT": "./datasets/robocasa_lerobot_V2.1",
13
+ "_ROBOCASA_ENV_SUFFIX": "_GR1ArmsAndWaistFourierHands_Env",
14
+ "_ROBOCASA_TASK_DIRS": [
15
+ "PnPBottleToCabinetClose",
16
+ "PnPCanToDrawerClose",
17
+ "PnPCupToDrawerClose",
18
+ "PnPMilkToMicrowaveClose",
19
+ "PnPPotatoToMicrowaveClose",
20
+ "PnPWineToCabinetClose",
21
+ "PosttrainPnPNovelFromCuttingboardToBasketSplitA",
22
+ "PosttrainPnPNovelFromCuttingboardToCardboardboxSplitA",
23
+ "PosttrainPnPNovelFromCuttingboardToPanSplitA",
24
+ "PosttrainPnPNovelFromCuttingboardToPotSplitA",
25
+ "PosttrainPnPNovelFromCuttingboardToTieredbasketSplitA",
26
+ "PosttrainPnPNovelFromPlacematToBasketSplitA",
27
+ "PosttrainPnPNovelFromPlacematToBowlSplitA",
28
+ "PosttrainPnPNovelFromPlacematToPlateSplitA",
29
+ "PosttrainPnPNovelFromPlacematToTieredshelfSplitA",
30
+ "PosttrainPnPNovelFromPlateToBowlSplitA",
31
+ "PosttrainPnPNovelFromPlateToCardboardboxSplitA",
32
+ "PosttrainPnPNovelFromPlateToPanSplitA",
33
+ "PosttrainPnPNovelFromPlateToPlateSplitA",
34
+ "PosttrainPnPNovelFromTrayToCardboardboxSplitA",
35
+ "PosttrainPnPNovelFromTrayToPlateSplitA",
36
+ "PosttrainPnPNovelFromTrayToPotSplitA",
37
+ "PosttrainPnPNovelFromTrayToTieredbasketSplitA",
38
+ "PosttrainPnPNovelFromTrayToTieredshelfSplitA"
39
+ ],
40
+ "_ROBOCASA_TASK_PREFIX": "gr1_unified",
41
+ "_SAVE_ITER_INTERVAL": 5000,
42
+ "_SHARED_ROBOCASA_DATA_ROOT": "/mnt/data/cpfs/mnt/data/yiming/fluxvla/datasets/robocasa_lerobot_V2.1",
43
+ "_SMOLVLA_CHECKPOINT": "./checkpoints/smolvla_base/model.safetensors",
44
+ "_SMOLVLA_TOKENIZER": "./checkpoints/SmolVLM2-500M-Video-Instruct",
45
+ "_STATISTIC_NAME": "robocasa_gr1_24tasks_absolute",
46
+ "_TOKENIZER": {
47
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
48
+ "type": "PretrainedTokenizer"
49
+ },
50
+ "_TRANSFORMS": [
51
+ {
52
+ "name_mappings": {
53
+ "actions": [
54
+ "actions"
55
+ ],
56
+ "observation.state": [
57
+ "states"
58
+ ]
59
+ },
60
+ "parquet_keys": [
61
+ "observation.state",
62
+ "timestamp",
63
+ "actions",
64
+ "info",
65
+ "stats",
66
+ "action_masks"
67
+ ],
68
+ "type": "ProcessParquetInputs",
69
+ "video_keys": [
70
+ "observation.images.ego_view"
71
+ ]
72
+ },
73
+ {
74
+ "action_dim": 32,
75
+ "action_key": "action",
76
+ "norm_type": "mean_std",
77
+ "state_dim": 32,
78
+ "state_key": "proprio",
79
+ "type": "NormalizeStatesAndActions"
80
+ },
81
+ {
82
+ "add_new_line": true,
83
+ "type": "ParquetPrompter",
84
+ "use_conversation": false
85
+ },
86
+ {
87
+ "tokenizer": {
88
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
89
+ "type": "PretrainedTokenizer"
90
+ },
91
+ "type": "ProcessPrompts"
92
+ },
93
+ {
94
+ "height": 512,
95
+ "pad_direction": "top-left",
96
+ "type": "ResizeImagesWithPad",
97
+ "width": 512
98
+ },
99
+ {
100
+ "type": "SimpleNormalizeImages"
101
+ }
102
+ ],
103
+ "eval": {
104
+ "action_order": "fluxvla",
105
+ "benchmark": "robocasa",
106
+ "dataset": {
107
+ "transforms": [
108
+ {
109
+ "center_crop_scale": null,
110
+ "img_key": "video.ego_view_bg_crop_pad_res256_freq20",
111
+ "normalize": false,
112
+ "resize_size": 512,
113
+ "type": "ProcessRobocasaEvalInputs"
114
+ },
115
+ {
116
+ "action_key": null,
117
+ "norm_type": "mean_std",
118
+ "state_dim": 32,
119
+ "state_key": "proprio",
120
+ "type": "NormalizeStatesAndActions"
121
+ },
122
+ {
123
+ "add_new_line": true,
124
+ "type": "ParquetPrompter",
125
+ "use_conversation": false
126
+ },
127
+ {
128
+ "tokenizer": {
129
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
130
+ "type": "PretrainedTokenizer"
131
+ },
132
+ "type": "ProcessPrompts"
133
+ },
134
+ {
135
+ "means": [
136
+ [
137
+ 127.5,
138
+ 127.5,
139
+ 127.5
140
+ ]
141
+ ],
142
+ "stds": [
143
+ [
144
+ 127.5,
145
+ 127.5,
146
+ 127.5
147
+ ]
148
+ ],
149
+ "type": "NormalizeImages"
150
+ }
151
+ ],
152
+ "type": "RobocasaEvalDataset",
153
+ "unnorm_key": "robocasa_gr1_24tasks_absolute"
154
+ },
155
+ "denormalize_action": {
156
+ "action_dim": 29,
157
+ "clip_actions": false,
158
+ "norm_type": "mean_std",
159
+ "stats_order": "native",
160
+ "type": "DenormalizeRobocasaAction"
161
+ },
162
+ "enable_mixed_precision_training": true,
163
+ "eval_chunk_size": 10,
164
+ "max_episode_steps": 720,
165
+ "mixed_precision_dtype": "bf16",
166
+ "model_family": "smolvla",
167
+ "num_trials_per_task": 20,
168
+ "seed": 7,
169
+ "task_list": [
170
+ "gr1_unified/PnPBottleToCabinetClose_GR1ArmsAndWaistFourierHands_Env",
171
+ "gr1_unified/PnPCanToDrawerClose_GR1ArmsAndWaistFourierHands_Env",
172
+ "gr1_unified/PnPCupToDrawerClose_GR1ArmsAndWaistFourierHands_Env",
173
+ "gr1_unified/PnPMilkToMicrowaveClose_GR1ArmsAndWaistFourierHands_Env",
174
+ "gr1_unified/PnPPotatoToMicrowaveClose_GR1ArmsAndWaistFourierHands_Env",
175
+ "gr1_unified/PnPWineToCabinetClose_GR1ArmsAndWaistFourierHands_Env",
176
+ "gr1_unified/PosttrainPnPNovelFromCuttingboardToBasketSplitA_GR1ArmsAndWaistFourierHands_Env",
177
+ "gr1_unified/PosttrainPnPNovelFromCuttingboardToCardboardboxSplitA_GR1ArmsAndWaistFourierHands_Env",
178
+ "gr1_unified/PosttrainPnPNovelFromCuttingboardToPanSplitA_GR1ArmsAndWaistFourierHands_Env",
179
+ "gr1_unified/PosttrainPnPNovelFromCuttingboardToPotSplitA_GR1ArmsAndWaistFourierHands_Env",
180
+ "gr1_unified/PosttrainPnPNovelFromCuttingboardToTieredbasketSplitA_GR1ArmsAndWaistFourierHands_Env",
181
+ "gr1_unified/PosttrainPnPNovelFromPlacematToBasketSplitA_GR1ArmsAndWaistFourierHands_Env",
182
+ "gr1_unified/PosttrainPnPNovelFromPlacematToBowlSplitA_GR1ArmsAndWaistFourierHands_Env",
183
+ "gr1_unified/PosttrainPnPNovelFromPlacematToPlateSplitA_GR1ArmsAndWaistFourierHands_Env",
184
+ "gr1_unified/PosttrainPnPNovelFromPlacematToTieredshelfSplitA_GR1ArmsAndWaistFourierHands_Env",
185
+ "gr1_unified/PosttrainPnPNovelFromPlateToBowlSplitA_GR1ArmsAndWaistFourierHands_Env",
186
+ "gr1_unified/PosttrainPnPNovelFromPlateToCardboardboxSplitA_GR1ArmsAndWaistFourierHands_Env",
187
+ "gr1_unified/PosttrainPnPNovelFromPlateToPanSplitA_GR1ArmsAndWaistFourierHands_Env",
188
+ "gr1_unified/PosttrainPnPNovelFromPlateToPlateSplitA_GR1ArmsAndWaistFourierHands_Env",
189
+ "gr1_unified/PosttrainPnPNovelFromTrayToCardboardboxSplitA_GR1ArmsAndWaistFourierHands_Env",
190
+ "gr1_unified/PosttrainPnPNovelFromTrayToPlateSplitA_GR1ArmsAndWaistFourierHands_Env",
191
+ "gr1_unified/PosttrainPnPNovelFromTrayToPotSplitA_GR1ArmsAndWaistFourierHands_Env",
192
+ "gr1_unified/PosttrainPnPNovelFromTrayToTieredbasketSplitA_GR1ArmsAndWaistFourierHands_Env",
193
+ "gr1_unified/PosttrainPnPNovelFromTrayToTieredshelfSplitA_GR1ArmsAndWaistFourierHands_Env"
194
+ ],
195
+ "task_suite_name": "robocasa",
196
+ "total_tasks": 24,
197
+ "type": "RobocasaEvalRunner",
198
+ "unnorm_key": "robocasa_gr1_24tasks_absolute"
199
+ },
200
+ "model": {
201
+ "action_in_proj": {
202
+ "in_dim": 32,
203
+ "out_dim": 720,
204
+ "type": "LinearProjector"
205
+ },
206
+ "action_out_proj": {
207
+ "in_dim": 720,
208
+ "out_dim": 32,
209
+ "type": "LinearProjector"
210
+ },
211
+ "action_time_mlp_in": {
212
+ "in_dim": 1440,
213
+ "out_dim": 720,
214
+ "type": "LinearProjector"
215
+ },
216
+ "action_time_mlp_out": {
217
+ "in_dim": 720,
218
+ "out_dim": 720,
219
+ "type": "LinearProjector"
220
+ },
221
+ "add_image_special_tokens": false,
222
+ "chunk_size": 50,
223
+ "freeze_vlm_backbone": true,
224
+ "llm_expert": {
225
+ "attention_bias": false,
226
+ "attention_mode": "cross_attn",
227
+ "head_dim": 64,
228
+ "hidden_act": "silu",
229
+ "hidden_size": 720,
230
+ "intermediate_size": -1,
231
+ "max_position_embeddings": 8192,
232
+ "num_attention_heads": 15,
233
+ "num_hidden_layers": 16,
234
+ "num_key_value_heads": 5,
235
+ "rms_norm_eps": 1e-05,
236
+ "self_attn_every_n_layers": 2,
237
+ "torch_dtype": "bfloat16",
238
+ "type": "SmolVLMExpert",
239
+ "vlm_kv_dim": 320,
240
+ "vocab_size": 49280
241
+ },
242
+ "max_action_dim": 32,
243
+ "name_mapping": {
244
+ "action_in_proj.projector": "model.action_in_proj",
245
+ "action_out_proj.projector": "model.action_out_proj",
246
+ "action_time_mlp_in.projector": "model.action_time_mlp_in",
247
+ "action_time_mlp_out.projector": "model.action_time_mlp_out",
248
+ "llm_expert.expert": "model.vlm_with_expert.lm_expert",
249
+ "state_proj.projector": "model.state_proj",
250
+ "vlm_backbone.vlm": "model.vlm_with_expert.vlm.model"
251
+ },
252
+ "num_steps": 10,
253
+ "ori_action_dim": 29,
254
+ "pretrained_name_or_path": "./checkpoints/smolvla_base/model.safetensors",
255
+ "state_proj": {
256
+ "in_dim": 32,
257
+ "out_dim": 960,
258
+ "type": "LinearProjector"
259
+ },
260
+ "type": "SmolVLAFlowMatching",
261
+ "vlm_backbone": {
262
+ "num_vlm_layers": 16,
263
+ "scale_factor": 4,
264
+ "text_config": {
265
+ "head_dim": 64,
266
+ "hidden_act": "silu",
267
+ "hidden_size": 960,
268
+ "intermediate_size": 2560,
269
+ "max_position_embeddings": 8192,
270
+ "num_attention_heads": 15,
271
+ "num_hidden_layers": 32,
272
+ "num_key_value_heads": 5,
273
+ "rms_norm_eps": 1e-05,
274
+ "vocab_size": 49280
275
+ },
276
+ "torch_dtype": "bfloat16",
277
+ "type": "SmolVLMBackbone",
278
+ "vision_config": {
279
+ "hidden_act": "gelu_pytorch_tanh",
280
+ "hidden_size": 768,
281
+ "image_size": 512,
282
+ "intermediate_size": 3072,
283
+ "layer_norm_eps": 1e-06,
284
+ "num_attention_heads": 12,
285
+ "num_hidden_layers": 12,
286
+ "patch_size": 16
287
+ }
288
+ }
289
+ },
290
+ "runner": {
291
+ "change_key_name": false,
292
+ "collator": {
293
+ "keys": [
294
+ "states",
295
+ "timestamp",
296
+ "images",
297
+ "img_masks",
298
+ "lang_tokens",
299
+ "lang_masks",
300
+ "actions",
301
+ "action_masks"
302
+ ],
303
+ "meta_keys": [
304
+ "task_description",
305
+ "prompt",
306
+ "info",
307
+ "stats"
308
+ ],
309
+ "type": "DictCollator"
310
+ },
311
+ "enable_gradient_checkpointing": true,
312
+ "enable_mixed_precision_training": true,
313
+ "lr_scheduler": {
314
+ "type": "linear-warmup+cosine-decay",
315
+ "warmup_ratio": 0.03
316
+ },
317
+ "max_grad_norm": 10.0,
318
+ "max_keep_ckpts": 2,
319
+ "max_steps": 100000,
320
+ "metric": {
321
+ "active_trackers": [
322
+ "jsonl",
323
+ "wandb"
324
+ ],
325
+ "run_dir": "work_dirs",
326
+ "type": "VLAMetric",
327
+ "window_size": 1
328
+ },
329
+ "mixed_precision_dtype": "bf16",
330
+ "optimizer": {
331
+ "lr": 0.0002,
332
+ "type": "AdamW",
333
+ "weight_decay": 0.0
334
+ },
335
+ "sampler": null,
336
+ "save_iter_interval": 5000,
337
+ "sharding_strategy": "no-shard",
338
+ "tokenizer": {
339
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
340
+ "type": "PretrainedTokenizer"
341
+ },
342
+ "type": "FSDPTrainRunner"
343
+ },
344
+ "train_dataloader": {
345
+ "dataset": {
346
+ "datasets": {
347
+ "action_key": "action",
348
+ "action_window_size": 50,
349
+ "data_root_path": [
350
+ "./datasets/robocasa_lerobot_V2.1/PnPBottleToCabinetClose",
351
+ "./datasets/robocasa_lerobot_V2.1/PnPCanToDrawerClose",
352
+ "./datasets/robocasa_lerobot_V2.1/PnPCupToDrawerClose",
353
+ "./datasets/robocasa_lerobot_V2.1/PnPMilkToMicrowaveClose",
354
+ "./datasets/robocasa_lerobot_V2.1/PnPPotatoToMicrowaveClose",
355
+ "./datasets/robocasa_lerobot_V2.1/PnPWineToCabinetClose",
356
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToBasketSplitA",
357
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToCardboardboxSplitA",
358
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToPanSplitA",
359
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToPotSplitA",
360
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToTieredbasketSplitA",
361
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlacematToBasketSplitA",
362
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlacematToBowlSplitA",
363
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlacematToPlateSplitA",
364
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlacematToTieredshelfSplitA",
365
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlateToBowlSplitA",
366
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlateToCardboardboxSplitA",
367
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlateToPanSplitA",
368
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlateToPlateSplitA",
369
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToCardboardboxSplitA",
370
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToPlateSplitA",
371
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToPotSplitA",
372
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToTieredbasketSplitA",
373
+ "./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToTieredshelfSplitA"
374
+ ],
375
+ "statistic_name": "robocasa_gr1_24tasks_absolute",
376
+ "supervise_terminal_padding": true,
377
+ "transforms": [
378
+ {
379
+ "name_mappings": {
380
+ "actions": [
381
+ "actions"
382
+ ],
383
+ "observation.state": [
384
+ "states"
385
+ ]
386
+ },
387
+ "parquet_keys": [
388
+ "observation.state",
389
+ "timestamp",
390
+ "actions",
391
+ "info",
392
+ "stats",
393
+ "action_masks"
394
+ ],
395
+ "type": "ProcessParquetInputs",
396
+ "video_keys": [
397
+ "observation.images.ego_view"
398
+ ]
399
+ },
400
+ {
401
+ "action_dim": 32,
402
+ "action_key": "action",
403
+ "norm_type": "mean_std",
404
+ "state_dim": 32,
405
+ "state_key": "proprio",
406
+ "type": "NormalizeStatesAndActions"
407
+ },
408
+ {
409
+ "add_new_line": true,
410
+ "type": "ParquetPrompter",
411
+ "use_conversation": false
412
+ },
413
+ {
414
+ "tokenizer": {
415
+ "model_path": "./checkpoints/SmolVLM2-500M-Video-Instruct",
416
+ "type": "PretrainedTokenizer"
417
+ },
418
+ "type": "ProcessPrompts"
419
+ },
420
+ {
421
+ "height": 512,
422
+ "pad_direction": "top-left",
423
+ "type": "ResizeImagesWithPad",
424
+ "width": 512
425
+ },
426
+ {
427
+ "type": "SimpleNormalizeImages"
428
+ }
429
+ ],
430
+ "type": "ParquetDataset",
431
+ "use_delta": false,
432
+ "window_start_idx": 0
433
+ },
434
+ "name_mappings": {
435
+ "action": [
436
+ "action"
437
+ ],
438
+ "observation.state": [
439
+ "proprio"
440
+ ]
441
+ },
442
+ "reshuffle_each_epoch": true,
443
+ "seed": 42,
444
+ "statistic_keys": [
445
+ "observation.state",
446
+ "timestamp",
447
+ "action"
448
+ ],
449
+ "statistic_name": "robocasa_gr1_24tasks_absolute",
450
+ "type": "DistributedBalancedRepeatingDataset"
451
+ },
452
+ "per_device_batch_size": 64,
453
+ "per_device_num_workers": 4
454
+ }
455
+ }
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/config.yaml ADDED
@@ -0,0 +1,363 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _ACTION_DIM: 29
2
+ _ACTION_HORIZON: 50
3
+ _CKPT_ROOT: ./checkpoints
4
+ _DEFAULT_ROBOCASA_DATA_ROOT: ./datasets/robocasa_lerobot_V2.1
5
+ _IMAGE_SIZE: 512
6
+ _LOCAL_ROBOCASA_DATA_ROOT: ./datasets/robocasa_lerobot_V2.1
7
+ _MAX_ACTION_DIM: 32
8
+ _MAX_STATE_DIM: 32
9
+ _MAX_STEPS: 100000
10
+ _PER_DEVICE_BATCH_SIZE: 64
11
+ _ROBOCASA_DATA_ROOT: ./datasets/robocasa_lerobot_V2.1
12
+ _ROBOCASA_ENV_SUFFIX: _GR1ArmsAndWaistFourierHands_Env
13
+ _ROBOCASA_TASK_DIRS:
14
+ - PnPBottleToCabinetClose
15
+ - PnPCanToDrawerClose
16
+ - PnPCupToDrawerClose
17
+ - PnPMilkToMicrowaveClose
18
+ - PnPPotatoToMicrowaveClose
19
+ - PnPWineToCabinetClose
20
+ - PosttrainPnPNovelFromCuttingboardToBasketSplitA
21
+ - PosttrainPnPNovelFromCuttingboardToCardboardboxSplitA
22
+ - PosttrainPnPNovelFromCuttingboardToPanSplitA
23
+ - PosttrainPnPNovelFromCuttingboardToPotSplitA
24
+ - PosttrainPnPNovelFromCuttingboardToTieredbasketSplitA
25
+ - PosttrainPnPNovelFromPlacematToBasketSplitA
26
+ - PosttrainPnPNovelFromPlacematToBowlSplitA
27
+ - PosttrainPnPNovelFromPlacematToPlateSplitA
28
+ - PosttrainPnPNovelFromPlacematToTieredshelfSplitA
29
+ - PosttrainPnPNovelFromPlateToBowlSplitA
30
+ - PosttrainPnPNovelFromPlateToCardboardboxSplitA
31
+ - PosttrainPnPNovelFromPlateToPanSplitA
32
+ - PosttrainPnPNovelFromPlateToPlateSplitA
33
+ - PosttrainPnPNovelFromTrayToCardboardboxSplitA
34
+ - PosttrainPnPNovelFromTrayToPlateSplitA
35
+ - PosttrainPnPNovelFromTrayToPotSplitA
36
+ - PosttrainPnPNovelFromTrayToTieredbasketSplitA
37
+ - PosttrainPnPNovelFromTrayToTieredshelfSplitA
38
+ _ROBOCASA_TASK_PREFIX: gr1_unified
39
+ _SAVE_ITER_INTERVAL: 5000
40
+ _SHARED_ROBOCASA_DATA_ROOT: /mnt/data/cpfs/mnt/data/yiming/fluxvla/datasets/robocasa_lerobot_V2.1
41
+ _SMOLVLA_CHECKPOINT: ./checkpoints/smolvla_base/model.safetensors
42
+ _SMOLVLA_TOKENIZER: ./checkpoints/SmolVLM2-500M-Video-Instruct
43
+ _STATISTIC_NAME: robocasa_gr1_24tasks_absolute
44
+ _TOKENIZER:
45
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
46
+ type: PretrainedTokenizer
47
+ _TRANSFORMS:
48
+ - name_mappings:
49
+ actions:
50
+ - actions
51
+ observation.state:
52
+ - states
53
+ parquet_keys:
54
+ - observation.state
55
+ - timestamp
56
+ - actions
57
+ - info
58
+ - stats
59
+ - action_masks
60
+ type: ProcessParquetInputs
61
+ video_keys:
62
+ - observation.images.ego_view
63
+ - action_dim: 32
64
+ action_key: action
65
+ norm_type: mean_std
66
+ state_dim: 32
67
+ state_key: proprio
68
+ type: NormalizeStatesAndActions
69
+ - add_new_line: true
70
+ type: ParquetPrompter
71
+ use_conversation: false
72
+ - tokenizer:
73
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
74
+ type: PretrainedTokenizer
75
+ type: ProcessPrompts
76
+ - height: 512
77
+ pad_direction: top-left
78
+ type: ResizeImagesWithPad
79
+ width: 512
80
+ - type: SimpleNormalizeImages
81
+ eval:
82
+ action_order: fluxvla
83
+ benchmark: robocasa
84
+ dataset:
85
+ transforms:
86
+ - center_crop_scale: null
87
+ img_key: video.ego_view_bg_crop_pad_res256_freq20
88
+ normalize: false
89
+ resize_size: 512
90
+ type: ProcessRobocasaEvalInputs
91
+ - action_key: null
92
+ norm_type: mean_std
93
+ state_dim: 32
94
+ state_key: proprio
95
+ type: NormalizeStatesAndActions
96
+ - add_new_line: true
97
+ type: ParquetPrompter
98
+ use_conversation: false
99
+ - tokenizer:
100
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
101
+ type: PretrainedTokenizer
102
+ type: ProcessPrompts
103
+ - means:
104
+ - - 127.5
105
+ - 127.5
106
+ - 127.5
107
+ stds:
108
+ - - 127.5
109
+ - 127.5
110
+ - 127.5
111
+ type: NormalizeImages
112
+ type: RobocasaEvalDataset
113
+ unnorm_key: robocasa_gr1_24tasks_absolute
114
+ denormalize_action:
115
+ action_dim: 29
116
+ clip_actions: false
117
+ norm_type: mean_std
118
+ stats_order: native
119
+ type: DenormalizeRobocasaAction
120
+ enable_mixed_precision_training: true
121
+ eval_chunk_size: 10
122
+ max_episode_steps: 720
123
+ mixed_precision_dtype: bf16
124
+ model_family: smolvla
125
+ num_trials_per_task: 20
126
+ seed: 7
127
+ task_list:
128
+ - gr1_unified/PnPBottleToCabinetClose_GR1ArmsAndWaistFourierHands_Env
129
+ - gr1_unified/PnPCanToDrawerClose_GR1ArmsAndWaistFourierHands_Env
130
+ - gr1_unified/PnPCupToDrawerClose_GR1ArmsAndWaistFourierHands_Env
131
+ - gr1_unified/PnPMilkToMicrowaveClose_GR1ArmsAndWaistFourierHands_Env
132
+ - gr1_unified/PnPPotatoToMicrowaveClose_GR1ArmsAndWaistFourierHands_Env
133
+ - gr1_unified/PnPWineToCabinetClose_GR1ArmsAndWaistFourierHands_Env
134
+ - gr1_unified/PosttrainPnPNovelFromCuttingboardToBasketSplitA_GR1ArmsAndWaistFourierHands_Env
135
+ - gr1_unified/PosttrainPnPNovelFromCuttingboardToCardboardboxSplitA_GR1ArmsAndWaistFourierHands_Env
136
+ - gr1_unified/PosttrainPnPNovelFromCuttingboardToPanSplitA_GR1ArmsAndWaistFourierHands_Env
137
+ - gr1_unified/PosttrainPnPNovelFromCuttingboardToPotSplitA_GR1ArmsAndWaistFourierHands_Env
138
+ - gr1_unified/PosttrainPnPNovelFromCuttingboardToTieredbasketSplitA_GR1ArmsAndWaistFourierHands_Env
139
+ - gr1_unified/PosttrainPnPNovelFromPlacematToBasketSplitA_GR1ArmsAndWaistFourierHands_Env
140
+ - gr1_unified/PosttrainPnPNovelFromPlacematToBowlSplitA_GR1ArmsAndWaistFourierHands_Env
141
+ - gr1_unified/PosttrainPnPNovelFromPlacematToPlateSplitA_GR1ArmsAndWaistFourierHands_Env
142
+ - gr1_unified/PosttrainPnPNovelFromPlacematToTieredshelfSplitA_GR1ArmsAndWaistFourierHands_Env
143
+ - gr1_unified/PosttrainPnPNovelFromPlateToBowlSplitA_GR1ArmsAndWaistFourierHands_Env
144
+ - gr1_unified/PosttrainPnPNovelFromPlateToCardboardboxSplitA_GR1ArmsAndWaistFourierHands_Env
145
+ - gr1_unified/PosttrainPnPNovelFromPlateToPanSplitA_GR1ArmsAndWaistFourierHands_Env
146
+ - gr1_unified/PosttrainPnPNovelFromPlateToPlateSplitA_GR1ArmsAndWaistFourierHands_Env
147
+ - gr1_unified/PosttrainPnPNovelFromTrayToCardboardboxSplitA_GR1ArmsAndWaistFourierHands_Env
148
+ - gr1_unified/PosttrainPnPNovelFromTrayToPlateSplitA_GR1ArmsAndWaistFourierHands_Env
149
+ - gr1_unified/PosttrainPnPNovelFromTrayToPotSplitA_GR1ArmsAndWaistFourierHands_Env
150
+ - gr1_unified/PosttrainPnPNovelFromTrayToTieredbasketSplitA_GR1ArmsAndWaistFourierHands_Env
151
+ - gr1_unified/PosttrainPnPNovelFromTrayToTieredshelfSplitA_GR1ArmsAndWaistFourierHands_Env
152
+ task_suite_name: robocasa
153
+ total_tasks: 24
154
+ type: RobocasaEvalRunner
155
+ unnorm_key: robocasa_gr1_24tasks_absolute
156
+ model:
157
+ action_in_proj:
158
+ in_dim: 32
159
+ out_dim: 720
160
+ type: LinearProjector
161
+ action_out_proj:
162
+ in_dim: 720
163
+ out_dim: 32
164
+ type: LinearProjector
165
+ action_time_mlp_in:
166
+ in_dim: 1440
167
+ out_dim: 720
168
+ type: LinearProjector
169
+ action_time_mlp_out:
170
+ in_dim: 720
171
+ out_dim: 720
172
+ type: LinearProjector
173
+ add_image_special_tokens: false
174
+ chunk_size: 50
175
+ freeze_vlm_backbone: true
176
+ llm_expert:
177
+ attention_bias: false
178
+ attention_mode: cross_attn
179
+ head_dim: 64
180
+ hidden_act: silu
181
+ hidden_size: 720
182
+ intermediate_size: -1
183
+ max_position_embeddings: 8192
184
+ num_attention_heads: 15
185
+ num_hidden_layers: 16
186
+ num_key_value_heads: 5
187
+ rms_norm_eps: 1.0e-05
188
+ self_attn_every_n_layers: 2
189
+ torch_dtype: bfloat16
190
+ type: SmolVLMExpert
191
+ vlm_kv_dim: 320
192
+ vocab_size: 49280
193
+ max_action_dim: 32
194
+ name_mapping:
195
+ action_in_proj.projector: model.action_in_proj
196
+ action_out_proj.projector: model.action_out_proj
197
+ action_time_mlp_in.projector: model.action_time_mlp_in
198
+ action_time_mlp_out.projector: model.action_time_mlp_out
199
+ llm_expert.expert: model.vlm_with_expert.lm_expert
200
+ state_proj.projector: model.state_proj
201
+ vlm_backbone.vlm: model.vlm_with_expert.vlm.model
202
+ num_steps: 10
203
+ ori_action_dim: 29
204
+ pretrained_name_or_path: ./checkpoints/smolvla_base/model.safetensors
205
+ state_proj:
206
+ in_dim: 32
207
+ out_dim: 960
208
+ type: LinearProjector
209
+ type: SmolVLAFlowMatching
210
+ vlm_backbone:
211
+ num_vlm_layers: 16
212
+ scale_factor: 4
213
+ text_config:
214
+ head_dim: 64
215
+ hidden_act: silu
216
+ hidden_size: 960
217
+ intermediate_size: 2560
218
+ max_position_embeddings: 8192
219
+ num_attention_heads: 15
220
+ num_hidden_layers: 32
221
+ num_key_value_heads: 5
222
+ rms_norm_eps: 1.0e-05
223
+ vocab_size: 49280
224
+ torch_dtype: bfloat16
225
+ type: SmolVLMBackbone
226
+ vision_config:
227
+ hidden_act: gelu_pytorch_tanh
228
+ hidden_size: 768
229
+ image_size: 512
230
+ intermediate_size: 3072
231
+ layer_norm_eps: 1.0e-06
232
+ num_attention_heads: 12
233
+ num_hidden_layers: 12
234
+ patch_size: 16
235
+ runner:
236
+ change_key_name: false
237
+ collator:
238
+ keys:
239
+ - states
240
+ - timestamp
241
+ - images
242
+ - img_masks
243
+ - lang_tokens
244
+ - lang_masks
245
+ - actions
246
+ - action_masks
247
+ meta_keys:
248
+ - task_description
249
+ - prompt
250
+ - info
251
+ - stats
252
+ type: DictCollator
253
+ enable_gradient_checkpointing: true
254
+ enable_mixed_precision_training: true
255
+ lr_scheduler:
256
+ type: linear-warmup+cosine-decay
257
+ warmup_ratio: 0.03
258
+ max_grad_norm: 10.0
259
+ max_keep_ckpts: 2
260
+ max_steps: 100000
261
+ metric:
262
+ active_trackers:
263
+ - jsonl
264
+ - wandb
265
+ run_dir: work_dirs
266
+ type: VLAMetric
267
+ window_size: 1
268
+ mixed_precision_dtype: bf16
269
+ optimizer:
270
+ lr: 0.0002
271
+ type: AdamW
272
+ weight_decay: 0.0
273
+ sampler: null
274
+ save_iter_interval: 5000
275
+ sharding_strategy: no-shard
276
+ tokenizer:
277
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
278
+ type: PretrainedTokenizer
279
+ type: FSDPTrainRunner
280
+ train_dataloader:
281
+ dataset:
282
+ datasets:
283
+ action_key: action
284
+ action_window_size: 50
285
+ data_root_path:
286
+ - ./datasets/robocasa_lerobot_V2.1/PnPBottleToCabinetClose
287
+ - ./datasets/robocasa_lerobot_V2.1/PnPCanToDrawerClose
288
+ - ./datasets/robocasa_lerobot_V2.1/PnPCupToDrawerClose
289
+ - ./datasets/robocasa_lerobot_V2.1/PnPMilkToMicrowaveClose
290
+ - ./datasets/robocasa_lerobot_V2.1/PnPPotatoToMicrowaveClose
291
+ - ./datasets/robocasa_lerobot_V2.1/PnPWineToCabinetClose
292
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToBasketSplitA
293
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToCardboardboxSplitA
294
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToPanSplitA
295
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToPotSplitA
296
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromCuttingboardToTieredbasketSplitA
297
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlacematToBasketSplitA
298
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlacematToBowlSplitA
299
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlacematToPlateSplitA
300
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlacematToTieredshelfSplitA
301
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlateToBowlSplitA
302
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlateToCardboardboxSplitA
303
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlateToPanSplitA
304
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromPlateToPlateSplitA
305
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToCardboardboxSplitA
306
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToPlateSplitA
307
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToPotSplitA
308
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToTieredbasketSplitA
309
+ - ./datasets/robocasa_lerobot_V2.1/PosttrainPnPNovelFromTrayToTieredshelfSplitA
310
+ statistic_name: robocasa_gr1_24tasks_absolute
311
+ supervise_terminal_padding: true
312
+ transforms:
313
+ - name_mappings:
314
+ actions:
315
+ - actions
316
+ observation.state:
317
+ - states
318
+ parquet_keys:
319
+ - observation.state
320
+ - timestamp
321
+ - actions
322
+ - info
323
+ - stats
324
+ - action_masks
325
+ type: ProcessParquetInputs
326
+ video_keys:
327
+ - observation.images.ego_view
328
+ - action_dim: 32
329
+ action_key: action
330
+ norm_type: mean_std
331
+ state_dim: 32
332
+ state_key: proprio
333
+ type: NormalizeStatesAndActions
334
+ - add_new_line: true
335
+ type: ParquetPrompter
336
+ use_conversation: false
337
+ - tokenizer:
338
+ model_path: ./checkpoints/SmolVLM2-500M-Video-Instruct
339
+ type: PretrainedTokenizer
340
+ type: ProcessPrompts
341
+ - height: 512
342
+ pad_direction: top-left
343
+ type: ResizeImagesWithPad
344
+ width: 512
345
+ - type: SimpleNormalizeImages
346
+ type: ParquetDataset
347
+ use_delta: false
348
+ window_start_idx: 0
349
+ name_mappings:
350
+ action:
351
+ - action
352
+ observation.state:
353
+ - proprio
354
+ reshuffle_each_epoch: true
355
+ seed: 42
356
+ statistic_keys:
357
+ - observation.state
358
+ - timestamp
359
+ - action
360
+ statistic_name: robocasa_gr1_24tasks_absolute
361
+ type: DistributedBalancedRepeatingDataset
362
+ per_device_batch_size: 64
363
+ per_device_num_workers: 4
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/dataset_statistics.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "robocasa_gr1_24tasks_absolute": {
3
+ "proprio": {
4
+ "mean": [
5
+ -0.17102599661465745,
6
+ 0.2351465922003492,
7
+ -0.11291017724669493,
8
+ -1.471245993840213,
9
+ 0.1778624544331975,
10
+ 0.10149730972614521,
11
+ -0.006413776953962568,
12
+ 0.1501827995850634,
13
+ 0.1494419544577889,
14
+ 0.13239416446275684,
15
+ 0.14923437345708596,
16
+ 0.03464704927495432,
17
+ 0.633716598676044,
18
+ -0.3203161989690995,
19
+ -0.3216767278916842,
20
+ 0.08499577598039175,
21
+ -1.472846504435421,
22
+ 0.33775973397171144,
23
+ 0.069097369998222,
24
+ 0.16150938098287304,
25
+ 0.4873080024446214,
26
+ 0.45776695630243025,
27
+ 0.4219260327763168,
28
+ 0.4522622699938164,
29
+ 0.07554572365420906,
30
+ 1.6688002354298241,
31
+ 0.0035976467853407854,
32
+ 0.00440595019181857,
33
+ -8.76750048672033e-05
34
+ ],
35
+ "std": [
36
+ 0.3752463888103661,
37
+ 0.1781493141251954,
38
+ 0.26539121353598727,
39
+ 0.4662220771042664,
40
+ 0.2902881388472991,
41
+ 0.285947325550312,
42
+ 0.3154311391949044,
43
+ 0.4183318014380274,
44
+ 0.4004064566977381,
45
+ 0.3536802979293458,
46
+ 0.4026344337086306,
47
+ 0.13890309097204462,
48
+ 0.8191262033093542,
49
+ 0.5024563669241094,
50
+ 0.2778612777044436,
51
+ 0.37864273717078883,
52
+ 0.6704838467418786,
53
+ 0.5231829479666285,
54
+ 0.3766345142399933,
55
+ 0.5706149895524781,
56
+ 0.5937571234718456,
57
+ 0.5513828952044627,
58
+ 0.5069913190612804,
59
+ 0.544104379096257,
60
+ 0.1702707998036827,
61
+ 0.2127909363186558,
62
+ 0.066217920981178,
63
+ 0.01964003934522461,
64
+ 0.007552978325307707
65
+ ],
66
+ "min": [
67
+ -1.6789460300197987,
68
+ -0.026101894167656833,
69
+ -1.3480229807275057,
70
+ -2.5160419455171383,
71
+ -1.9940674293626888,
72
+ -1.3795876165424843,
73
+ -1.1958755614665564,
74
+ -1.4389893440386452,
75
+ -1.8303323573520742,
76
+ -2.463510899514718,
77
+ -1.7167329202498351,
78
+ -2.2188928213939314,
79
+ -1.5269250161501569,
80
+ -2.0664756743527475,
81
+ -2.102197548050542,
82
+ -2.296651552249,
83
+ -2.5318210932848517,
84
+ -3.0013695261878524,
85
+ -1.4908946487722965,
86
+ -1.2908861768348467,
87
+ -1.4716512093880627,
88
+ -2.017198461431526,
89
+ -2.4121232309556744,
90
+ -1.1890256795135683,
91
+ -0.8325809657745491,
92
+ -0.21484142668648748,
93
+ -0.5222951662090487,
94
+ -0.42820973013578145,
95
+ -0.3979122252676978
96
+ ],
97
+ "max": [
98
+ 1.3502350045737779,
99
+ 1.2633577197721537,
100
+ 1.2589014167981796,
101
+ 0.001734813467578475,
102
+ 2.521491195625066,
103
+ 1.5269985370174448,
104
+ 1.496475292119885,
105
+ 2.017945519693373,
106
+ 2.009377962806827,
107
+ 2.619651476689811,
108
+ 1.8978251206699477,
109
+ 3.215102851458693,
110
+ 2.7924649534703327,
111
+ 1.5148204036582702,
112
+ 0.003278259824191162,
113
+ 1.7851011591253052,
114
+ 0.0016116080154506653,
115
+ 3.0015334255795847,
116
+ 1.4080945026607214,
117
+ 1.4516682564050527,
118
+ 2.7859505569280185,
119
+ 2.1664255772517858,
120
+ 3.01313575789069,
121
+ 2.698666894502952,
122
+ 1.4733597233873472,
123
+ 2.0798482608555853,
124
+ 0.9376961154285229,
125
+ 0.3457968140450505,
126
+ 0.47687002583669513
127
+ ],
128
+ "q01": null,
129
+ "q99": null
130
+ },
131
+ "timestamp": {
132
+ "mean": [
133
+ 6.9375469339818805
134
+ ],
135
+ "std": [
136
+ 4.952016725677098
137
+ ],
138
+ "min": [
139
+ 0.0
140
+ ],
141
+ "max": [
142
+ 27.99997329711914
143
+ ],
144
+ "q01": null,
145
+ "q99": null
146
+ },
147
+ "action": {
148
+ "mean": [
149
+ -0.17387279212408005,
150
+ 0.2317959863122206,
151
+ -0.11246790338103844,
152
+ -1.467062713309252,
153
+ 0.17808052074051176,
154
+ 0.09697908865733634,
155
+ -0.0060607796254134524,
156
+ -0.2245450957449247,
157
+ -0.2245450957449247,
158
+ -0.2245450957449247,
159
+ -0.2245450957449247,
160
+ -0.4490901914898494,
161
+ 1.1117459333448283,
162
+ -0.32863753584743216,
163
+ -0.32352645485453274,
164
+ 0.0782404261609689,
165
+ -1.4673430410272539,
166
+ 0.34360056400792244,
167
+ 0.07368263951697931,
168
+ 0.17824670307861504,
169
+ -0.4775669935405938,
170
+ -0.4775669935405938,
171
+ -0.4775669935405938,
172
+ -0.4775669935405938,
173
+ -0.9551339870811876,
174
+ 3.0,
175
+ 0.0036528567343992314,
176
+ 0.006440046858644384,
177
+ -0.00022533835530778442
178
+ ],
179
+ "std": [
180
+ 0.3826171317806213,
181
+ 0.17815629624675747,
182
+ 0.26800661573393214,
183
+ 0.4803447241741419,
184
+ 0.2980456830294638,
185
+ 0.29260705044489294,
186
+ 0.32540822440543915,
187
+ 0.8850926222636396,
188
+ 0.8850926222636396,
189
+ 0.8850926222636396,
190
+ 0.8850926222636396,
191
+ 1.7701852445272792,
192
+ 1.4488819067562586,
193
+ 0.5155028607609987,
194
+ 0.28702223677444855,
195
+ 0.39341085414345633,
196
+ 0.7028457071670143,
197
+ 0.5286721911865871,
198
+ 0.3970307944625585,
199
+ 0.6155327132847032,
200
+ 1.421945767840926,
201
+ 1.421945767840926,
202
+ 1.421945767840926,
203
+ 1.421945767840926,
204
+ 2.843891535681852,
205
+ 0.0,
206
+ 0.0695613329325858,
207
+ 0.020306337852383453,
208
+ 0.0054645999469296385
209
+ ],
210
+ "min": [
211
+ -1.7102377303085174,
212
+ -0.0004263203810975398,
213
+ -1.4035195516648833,
214
+ -2.8013732811426135,
215
+ -2.033860552463148,
216
+ -1.4939793808271242,
217
+ -1.3439968738771535,
218
+ -1.5,
219
+ -1.5,
220
+ -1.5,
221
+ -1.5,
222
+ -3.0,
223
+ 0.0,
224
+ -2.102059126731388,
225
+ -2.201687041945825,
226
+ -2.300512214043844,
227
+ -2.848569658957113,
228
+ -3.0000684763093926,
229
+ -1.4995447324386149,
230
+ -1.4891802904310267,
231
+ -1.5,
232
+ -1.5,
233
+ -1.5,
234
+ -1.5,
235
+ -3.0,
236
+ 3.0,
237
+ -0.5332962683304875,
238
+ -0.49477449959999975,
239
+ -0.41288947603278703
240
+ ],
241
+ "max": [
242
+ 1.40583034950624,
243
+ 1.2888770353485717,
244
+ 1.2944501673015227,
245
+ 3.1500877157135534e-06,
246
+ 2.5635940392491756,
247
+ 1.500028569769765,
248
+ 1.4998135201156853,
249
+ 1.5,
250
+ 1.5,
251
+ 1.5,
252
+ 1.5,
253
+ 3.0,
254
+ 3.0,
255
+ 1.564226484545798,
256
+ 0.0001545432449885152,
257
+ 1.7984894521519637,
258
+ 5.365317978462737e-05,
259
+ 3.000076671278979,
260
+ 1.495404725133036,
261
+ 1.4975834128202525,
262
+ 1.5,
263
+ 1.5,
264
+ 1.5,
265
+ 1.5,
266
+ 3.0,
267
+ 3.0,
268
+ 0.9750414444521461,
269
+ 0.3477231778875215,
270
+ 0.5310259525906885
271
+ ],
272
+ "q01": null,
273
+ "q99": null
274
+ }
275
+ }
276
+ }
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 49279,
3
+ "<fake_token_around_image>": 49189,
4
+ "<global-img>": 49152,
5
+ "<image>": 49190,
6
+ "<row_1_col_1>": 49153,
7
+ "<row_1_col_2>": 49154,
8
+ "<row_1_col_3>": 49155,
9
+ "<row_1_col_4>": 49156,
10
+ "<row_1_col_5>": 49157,
11
+ "<row_1_col_6>": 49158,
12
+ "<row_2_col_1>": 49159,
13
+ "<row_2_col_2>": 49160,
14
+ "<row_2_col_3>": 49161,
15
+ "<row_2_col_4>": 49162,
16
+ "<row_2_col_5>": 49163,
17
+ "<row_2_col_6>": 49164,
18
+ "<row_3_col_1>": 49165,
19
+ "<row_3_col_2>": 49166,
20
+ "<row_3_col_3>": 49167,
21
+ "<row_3_col_4>": 49168,
22
+ "<row_3_col_5>": 49169,
23
+ "<row_3_col_6>": 49170,
24
+ "<row_4_col_1>": 49171,
25
+ "<row_4_col_2>": 49172,
26
+ "<row_4_col_3>": 49173,
27
+ "<row_4_col_4>": 49174,
28
+ "<row_4_col_5>": 49175,
29
+ "<row_4_col_6>": 49176,
30
+ "<row_5_col_1>": 49177,
31
+ "<row_5_col_2>": 49178,
32
+ "<row_5_col_3>": 49179,
33
+ "<row_5_col_4>": 49180,
34
+ "<row_5_col_5>": 49181,
35
+ "<row_5_col_6>": 49182,
36
+ "<row_6_col_1>": 49183,
37
+ "<row_6_col_2>": 49184,
38
+ "<row_6_col_3>": 49185,
39
+ "<row_6_col_4>": 49186,
40
+ "<row_6_col_5>": 49187,
41
+ "<row_6_col_6>": 49188,
42
+ "<|reserved_special_token_0|>": 49191,
43
+ "<|reserved_special_token_10|>": 49201,
44
+ "<|reserved_special_token_11|>": 49202,
45
+ "<|reserved_special_token_12|>": 49203,
46
+ "<|reserved_special_token_13|>": 49204,
47
+ "<|reserved_special_token_14|>": 49205,
48
+ "<|reserved_special_token_15|>": 49206,
49
+ "<|reserved_special_token_16|>": 49207,
50
+ "<|reserved_special_token_17|>": 49208,
51
+ "<|reserved_special_token_18|>": 49209,
52
+ "<|reserved_special_token_19|>": 49210,
53
+ "<|reserved_special_token_1|>": 49192,
54
+ "<|reserved_special_token_20|>": 49211,
55
+ "<|reserved_special_token_21|>": 49212,
56
+ "<|reserved_special_token_22|>": 49213,
57
+ "<|reserved_special_token_23|>": 49214,
58
+ "<|reserved_special_token_24|>": 49215,
59
+ "<|reserved_special_token_25|>": 49216,
60
+ "<|reserved_special_token_26|>": 49217,
61
+ "<|reserved_special_token_27|>": 49218,
62
+ "<|reserved_special_token_28|>": 49219,
63
+ "<|reserved_special_token_29|>": 49220,
64
+ "<|reserved_special_token_2|>": 49193,
65
+ "<|reserved_special_token_30|>": 49221,
66
+ "<|reserved_special_token_31|>": 49222,
67
+ "<|reserved_special_token_32|>": 49223,
68
+ "<|reserved_special_token_33|>": 49224,
69
+ "<|reserved_special_token_34|>": 49225,
70
+ "<|reserved_special_token_35|>": 49226,
71
+ "<|reserved_special_token_36|>": 49227,
72
+ "<|reserved_special_token_37|>": 49228,
73
+ "<|reserved_special_token_38|>": 49229,
74
+ "<|reserved_special_token_39|>": 49230,
75
+ "<|reserved_special_token_3|>": 49194,
76
+ "<|reserved_special_token_40|>": 49231,
77
+ "<|reserved_special_token_41|>": 49232,
78
+ "<|reserved_special_token_42|>": 49233,
79
+ "<|reserved_special_token_43|>": 49234,
80
+ "<|reserved_special_token_44|>": 49235,
81
+ "<|reserved_special_token_45|>": 49236,
82
+ "<|reserved_special_token_46|>": 49237,
83
+ "<|reserved_special_token_47|>": 49238,
84
+ "<|reserved_special_token_48|>": 49239,
85
+ "<|reserved_special_token_49|>": 49240,
86
+ "<|reserved_special_token_4|>": 49195,
87
+ "<|reserved_special_token_50|>": 49241,
88
+ "<|reserved_special_token_51|>": 49242,
89
+ "<|reserved_special_token_52|>": 49243,
90
+ "<|reserved_special_token_53|>": 49244,
91
+ "<|reserved_special_token_54|>": 49245,
92
+ "<|reserved_special_token_55|>": 49246,
93
+ "<|reserved_special_token_56|>": 49247,
94
+ "<|reserved_special_token_57|>": 49248,
95
+ "<|reserved_special_token_58|>": 49249,
96
+ "<|reserved_special_token_59|>": 49250,
97
+ "<|reserved_special_token_5|>": 49196,
98
+ "<|reserved_special_token_60|>": 49251,
99
+ "<|reserved_special_token_61|>": 49252,
100
+ "<|reserved_special_token_62|>": 49253,
101
+ "<|reserved_special_token_63|>": 49254,
102
+ "<|reserved_special_token_64|>": 49255,
103
+ "<|reserved_special_token_65|>": 49256,
104
+ "<|reserved_special_token_66|>": 49257,
105
+ "<|reserved_special_token_67|>": 49258,
106
+ "<|reserved_special_token_68|>": 49259,
107
+ "<|reserved_special_token_69|>": 49260,
108
+ "<|reserved_special_token_6|>": 49197,
109
+ "<|reserved_special_token_70|>": 49261,
110
+ "<|reserved_special_token_71|>": 49262,
111
+ "<|reserved_special_token_72|>": 49263,
112
+ "<|reserved_special_token_73|>": 49264,
113
+ "<|reserved_special_token_74|>": 49265,
114
+ "<|reserved_special_token_75|>": 49266,
115
+ "<|reserved_special_token_76|>": 49267,
116
+ "<|reserved_special_token_77|>": 49268,
117
+ "<|reserved_special_token_78|>": 49269,
118
+ "<|reserved_special_token_79|>": 49270,
119
+ "<|reserved_special_token_7|>": 49198,
120
+ "<|reserved_special_token_80|>": 49271,
121
+ "<|reserved_special_token_81|>": 49272,
122
+ "<|reserved_special_token_82|>": 49273,
123
+ "<|reserved_special_token_83|>": 49274,
124
+ "<|reserved_special_token_84|>": 49275,
125
+ "<|reserved_special_token_85|>": 49276,
126
+ "<|reserved_special_token_86|>": 49277,
127
+ "<|reserved_special_token_87|>": 49278,
128
+ "<|reserved_special_token_8|>": 49199,
129
+ "<|reserved_special_token_9|>": 49200
130
+ }
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
3
+ }
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/chat_template.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ 1d342e4f070c962a14ba4ece4e06212bc70d8e36
3
+ 1788174017.1410778
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/merges.txt.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ 69503b13f727ba3812b6803e97442a6de05ef5eb
3
+ 1788174017.528027
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<fake_token_around_image>",
4
+ "<image>",
5
+ "<end_of_utterance>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|im_start|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "end_of_utterance_token": "<end_of_utterance>",
15
+ "eos_token": {
16
+ "content": "<end_of_utterance>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "fake_image_token": "<fake_token_around_image>",
23
+ "global_image_token": "<global-img>",
24
+ "image_token": "<image>",
25
+ "pad_token": {
26
+ "content": "<|im_end|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/tokenizer.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ a4005d1cf3170a31600a5c96f95768166cbc2b28
3
+ 1788174035.4913952
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,1192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49152": {
141
+ "content": "<global-img>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49153": {
149
+ "content": "<row_1_col_1>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49154": {
157
+ "content": "<row_1_col_2>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49155": {
165
+ "content": "<row_1_col_3>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49156": {
173
+ "content": "<row_1_col_4>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49157": {
181
+ "content": "<row_1_col_5>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "49158": {
189
+ "content": "<row_1_col_6>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "49159": {
197
+ "content": "<row_2_col_1>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "49160": {
205
+ "content": "<row_2_col_2>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "49161": {
213
+ "content": "<row_2_col_3>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "49162": {
221
+ "content": "<row_2_col_4>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "49163": {
229
+ "content": "<row_2_col_5>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "49164": {
237
+ "content": "<row_2_col_6>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "49165": {
245
+ "content": "<row_3_col_1>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "49166": {
253
+ "content": "<row_3_col_2>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "49167": {
261
+ "content": "<row_3_col_3>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "49168": {
269
+ "content": "<row_3_col_4>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "49169": {
277
+ "content": "<row_3_col_5>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "49170": {
285
+ "content": "<row_3_col_6>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "49171": {
293
+ "content": "<row_4_col_1>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "49172": {
301
+ "content": "<row_4_col_2>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "49173": {
309
+ "content": "<row_4_col_3>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "49174": {
317
+ "content": "<row_4_col_4>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "49175": {
325
+ "content": "<row_4_col_5>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "49176": {
333
+ "content": "<row_4_col_6>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "49177": {
341
+ "content": "<row_5_col_1>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "49178": {
349
+ "content": "<row_5_col_2>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "49179": {
357
+ "content": "<row_5_col_3>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "49180": {
365
+ "content": "<row_5_col_4>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "49181": {
373
+ "content": "<row_5_col_5>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "49182": {
381
+ "content": "<row_5_col_6>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "49183": {
389
+ "content": "<row_6_col_1>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "49184": {
397
+ "content": "<row_6_col_2>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "49185": {
405
+ "content": "<row_6_col_3>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "49186": {
413
+ "content": "<row_6_col_4>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "49187": {
421
+ "content": "<row_6_col_5>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "49188": {
429
+ "content": "<row_6_col_6>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "49189": {
437
+ "content": "<fake_token_around_image>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "49190": {
445
+ "content": "<image>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "49191": {
453
+ "content": "<|reserved_special_token_0|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "49192": {
461
+ "content": "<|reserved_special_token_1|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "49193": {
469
+ "content": "<|reserved_special_token_2|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "49194": {
477
+ "content": "<|reserved_special_token_3|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "49195": {
485
+ "content": "<|reserved_special_token_4|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "49196": {
493
+ "content": "<|reserved_special_token_5|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "49197": {
501
+ "content": "<|reserved_special_token_6|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "49198": {
509
+ "content": "<|reserved_special_token_7|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "49199": {
517
+ "content": "<|reserved_special_token_8|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "49200": {
525
+ "content": "<|reserved_special_token_9|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "49201": {
533
+ "content": "<|reserved_special_token_10|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "49202": {
541
+ "content": "<|reserved_special_token_11|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "49203": {
549
+ "content": "<|reserved_special_token_12|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "49204": {
557
+ "content": "<|reserved_special_token_13|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "49205": {
565
+ "content": "<|reserved_special_token_14|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "49206": {
573
+ "content": "<|reserved_special_token_15|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "49207": {
581
+ "content": "<|reserved_special_token_16|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "49208": {
589
+ "content": "<|reserved_special_token_17|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "49209": {
597
+ "content": "<|reserved_special_token_18|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "49210": {
605
+ "content": "<|reserved_special_token_19|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "49211": {
613
+ "content": "<|reserved_special_token_20|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "49212": {
621
+ "content": "<|reserved_special_token_21|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "49213": {
629
+ "content": "<|reserved_special_token_22|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "49214": {
637
+ "content": "<|reserved_special_token_23|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "49215": {
645
+ "content": "<|reserved_special_token_24|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "49216": {
653
+ "content": "<|reserved_special_token_25|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "49217": {
661
+ "content": "<|reserved_special_token_26|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "49218": {
669
+ "content": "<|reserved_special_token_27|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "49219": {
677
+ "content": "<|reserved_special_token_28|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "49220": {
685
+ "content": "<|reserved_special_token_29|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "49221": {
693
+ "content": "<|reserved_special_token_30|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "49222": {
701
+ "content": "<|reserved_special_token_31|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "49223": {
709
+ "content": "<|reserved_special_token_32|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "49224": {
717
+ "content": "<|reserved_special_token_33|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "49225": {
725
+ "content": "<|reserved_special_token_34|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "49226": {
733
+ "content": "<|reserved_special_token_35|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "49227": {
741
+ "content": "<|reserved_special_token_36|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "49228": {
749
+ "content": "<|reserved_special_token_37|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "49229": {
757
+ "content": "<|reserved_special_token_38|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "49230": {
765
+ "content": "<|reserved_special_token_39|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "49231": {
773
+ "content": "<|reserved_special_token_40|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "49232": {
781
+ "content": "<|reserved_special_token_41|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "49233": {
789
+ "content": "<|reserved_special_token_42|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "49234": {
797
+ "content": "<|reserved_special_token_43|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "49235": {
805
+ "content": "<|reserved_special_token_44|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "49236": {
813
+ "content": "<|reserved_special_token_45|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "49237": {
821
+ "content": "<|reserved_special_token_46|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "49238": {
829
+ "content": "<|reserved_special_token_47|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "49239": {
837
+ "content": "<|reserved_special_token_48|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "49240": {
845
+ "content": "<|reserved_special_token_49|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "49241": {
853
+ "content": "<|reserved_special_token_50|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "49242": {
861
+ "content": "<|reserved_special_token_51|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "49243": {
869
+ "content": "<|reserved_special_token_52|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "49244": {
877
+ "content": "<|reserved_special_token_53|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "49245": {
885
+ "content": "<|reserved_special_token_54|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "49246": {
893
+ "content": "<|reserved_special_token_55|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "49247": {
901
+ "content": "<|reserved_special_token_56|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "49248": {
909
+ "content": "<|reserved_special_token_57|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "49249": {
917
+ "content": "<|reserved_special_token_58|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "49250": {
925
+ "content": "<|reserved_special_token_59|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "49251": {
933
+ "content": "<|reserved_special_token_60|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "49252": {
941
+ "content": "<|reserved_special_token_61|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "49253": {
949
+ "content": "<|reserved_special_token_62|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "49254": {
957
+ "content": "<|reserved_special_token_63|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "49255": {
965
+ "content": "<|reserved_special_token_64|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "49256": {
973
+ "content": "<|reserved_special_token_65|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "49257": {
981
+ "content": "<|reserved_special_token_66|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "49258": {
989
+ "content": "<|reserved_special_token_67|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "49259": {
997
+ "content": "<|reserved_special_token_68|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "49260": {
1005
+ "content": "<|reserved_special_token_69|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "49261": {
1013
+ "content": "<|reserved_special_token_70|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "49262": {
1021
+ "content": "<|reserved_special_token_71|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "49263": {
1029
+ "content": "<|reserved_special_token_72|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "49264": {
1037
+ "content": "<|reserved_special_token_73|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "49265": {
1045
+ "content": "<|reserved_special_token_74|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "49266": {
1053
+ "content": "<|reserved_special_token_75|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "49267": {
1061
+ "content": "<|reserved_special_token_76|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "49268": {
1069
+ "content": "<|reserved_special_token_77|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "49269": {
1077
+ "content": "<|reserved_special_token_78|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "49270": {
1085
+ "content": "<|reserved_special_token_79|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "49271": {
1093
+ "content": "<|reserved_special_token_80|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "49272": {
1101
+ "content": "<|reserved_special_token_81|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "49273": {
1109
+ "content": "<|reserved_special_token_82|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "49274": {
1117
+ "content": "<|reserved_special_token_83|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "49275": {
1125
+ "content": "<|reserved_special_token_84|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "49276": {
1133
+ "content": "<|reserved_special_token_85|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "49277": {
1141
+ "content": "<|reserved_special_token_86|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "49278": {
1149
+ "content": "<|reserved_special_token_87|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "49279": {
1157
+ "content": "<end_of_utterance>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ }
1164
+ },
1165
+ "additional_special_tokens": [
1166
+ "<fake_token_around_image>",
1167
+ "<image>",
1168
+ "<end_of_utterance>"
1169
+ ],
1170
+ "bos_token": "<|im_start|>",
1171
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
1172
+ "clean_up_tokenization_spaces": false,
1173
+ "end_of_utterance_token": "<end_of_utterance>",
1174
+ "eos_token": "<end_of_utterance>",
1175
+ "extra_special_tokens": {
1176
+ "end_of_utterance_token": "<end_of_utterance>",
1177
+ "fake_image_token": "<fake_token_around_image>",
1178
+ "global_image_token": "<global-img>",
1179
+ "image_token": "<image>"
1180
+ },
1181
+ "fake_image_token": "<fake_token_around_image>",
1182
+ "global_image_token": "<global-img>",
1183
+ "image_token": "<image>",
1184
+ "legacy": false,
1185
+ "model_max_length": 8192,
1186
+ "pad_token": "<|im_end|>",
1187
+ "processor_class": "SmolVLMProcessor",
1188
+ "tokenizer_class": "GPT2Tokenizer",
1189
+ "truncation_side": "left",
1190
+ "unk_token": "<|endoftext|>",
1191
+ "vocab_size": 49152
1192
+ }
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/tokenizer_config.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ e4042a1126290fdb96ece2a4ad8dd7108c5de484
3
+ 1788174035.8630807
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/tokenizer/vocab.json.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ 7b375e1b73b11138ff12fe22c8f2822d8fe03467
2
+ 0ad5ecc2035b7031b88afb544ee95e2d49baa484
3
+ 1788174036.0744355
smolvla_robocasa_full_data_finetune_freeze_vlm_bs512/vlm_backbone_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "bos_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "head_dim": 64,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 960,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 2560,
11
+ "max_position_embeddings": 8192,
12
+ "mlp_bias": false,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 15,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 5,
17
+ "pad_token_id": null,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_parameters": {
21
+ "rope_theta": 10000.0,
22
+ "rope_type": "default"
23
+ },
24
+ "tie_word_embeddings": false,
25
+ "transformers_version": "5.3.0",
26
+ "use_cache": true,
27
+ "vocab_size": 49280
28
+ }