Hugging Face's logo

Seaman05
/
temp2

Safetensors
beingh
Model card Files
xet
 Community
temp2
File size: 9,995 Bytes
3ec15e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
{
  "return_dict": true,
  "output_hidden_states": false,
  "torchscript": false,
  "dtype": null,
  "pruned_heads": {},
  "tie_word_embeddings": true,
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "is_decoder": false,
  "cross_attention_hidden_size": null,
  "add_cross_attention": false,
  "tie_encoder_decoder": false,
  "architectures": null,
  "finetuning_task": null,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "task_specific_params": null,
  "problem_type": null,
  "tokenizer_class": null,
  "prefix": null,
  "bos_token_id": null,
  "pad_token_id": null,
  "eos_token_id": null,
  "sep_token_id": null,
  "decoder_start_token_id": null,
  "max_length": 20,
  "min_length": 0,
  "do_sample": false,
  "early_stopping": false,
  "num_beams": 1,
  "temperature": 1.0,
  "top_k": 50,
  "top_p": 1.0,
  "typical_p": 1.0,
  "repetition_penalty": 1.0,
  "length_penalty": 1.0,
  "no_repeat_ngram_size": 0,
  "encoder_no_repeat_ngram_size": 0,
  "bad_words_ids": null,
  "num_return_sequences": 1,
  "output_scores": false,
  "return_dict_in_generate": false,
  "forced_bos_token_id": null,
  "forced_eos_token_id": null,
  "remove_invalid_values": false,
  "exponential_decay_length_penalty": null,
  "suppress_tokens": null,
  "begin_suppress_tokens": null,
  "num_beam_groups": 1,
  "diversity_penalty": 0.0,
  "_name_or_path": "",
  "transformers_version": "4.57.1",
  "use_mpg": true,
  "mpg_num_projections": 32,
  "mpg_lambda": 0.1,
  "mpg_use_stop_gradient": true,
  "mpg_refinement_iters": 1,
  "mpg_gate_temperature": 1.0,
  "use_training_time_rtc": false,
  "simulated_delay": 0,
  "rtc_delay_exp_weight": true,
  "use_inference_prefix_overwrite": true,
  "tf_legacy_loss": false,
  "use_bfloat16": false,
  "llm_config": {
    "vocab_size": 151701,
    "max_position_embeddings": 40960,
    "hidden_size": 2048,
    "intermediate_size": 6144,
    "num_hidden_layers": 28,
    "num_attention_heads": 16,
    "use_sliding_window": false,
    "sliding_window": null,
    "max_window_layers": 28,
    "num_key_value_heads": 8,
    "hidden_act": "silu",
    "initializer_range": 0.02,
    "rms_norm_eps": 1e-06,
    "use_cache": false,
    "rope_theta": 1000000,
    "rope_scaling": null,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "is_causal": true,
    "return_dict": true,
    "output_hidden_states": false,
    "torchscript": false,
    "dtype": "bfloat16",
    "pruned_heads": {},
    "tie_word_embeddings": false,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "is_decoder": false,
    "cross_attention_hidden_size": null,
    "add_cross_attention": false,
    "tie_encoder_decoder": false,
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "finetuning_task": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "task_specific_params": null,
    "problem_type": null,
    "tokenizer_class": null,
    "prefix": null,
    "bos_token_id": 151643,
    "pad_token_id": null,
    "eos_token_id": 151645,
    "sep_token_id": null,
    "decoder_start_token_id": null,
    "max_length": 20,
    "min_length": 0,
    "do_sample": false,
    "early_stopping": false,
    "num_beams": 1,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "encoder_no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "num_return_sequences": 1,
    "output_scores": false,
    "return_dict_in_generate": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": null,
    "begin_suppress_tokens": null,
    "num_beam_groups": 1,
    "diversity_penalty": 0.0,
    "_name_or_path": "/root/codespace/checkpoints/Qwen3-1.7B",
    "debug": false,
    "ep_size": 1,
    "head_dim": 128,
    "micro_forward": false,
    "model_type": "qwen3",
    "skip_checkpoint": false,
    "use_deepep": false,
    "tf_legacy_loss": false,
    "use_bfloat16": false,
    "qk_norm": true,
    "layer_module": "Qwen3MoTDecoderLayer",
    "use_mot": true,
    "expert_config": {
      "vocab_size": 151936,
      "max_position_embeddings": 40960,
      "hidden_size": 1024,
      "intermediate_size": 3072,
      "num_hidden_layers": 28,
      "num_attention_heads": 16,
      "use_sliding_window": false,
      "sliding_window": null,
      "max_window_layers": 28,
      "num_key_value_heads": 8,
      "hidden_act": "silu",
      "initializer_range": 0.02,
      "rms_norm_eps": 1e-06,
      "use_cache": true,
      "rope_theta": 1000000,
      "rope_scaling": null,
      "attention_bias": false,
      "attention_dropout": 0.0,
      "is_causal": true,
      "return_dict": true,
      "output_hidden_states": false,
      "torchscript": false,
      "dtype": "bfloat16",
      "pruned_heads": {},
      "tie_word_embeddings": true,
      "chunk_size_feed_forward": 0,
      "is_encoder_decoder": false,
      "is_decoder": false,
      "cross_attention_hidden_size": null,
      "add_cross_attention": false,
      "tie_encoder_decoder": false,
      "architectures": [
        "Qwen3ForCausalLM"
      ],
      "finetuning_task": null,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "task_specific_params": null,
      "problem_type": null,
      "tokenizer_class": null,
      "prefix": null,
      "bos_token_id": 151643,
      "pad_token_id": null,
      "eos_token_id": 151645,
      "sep_token_id": null,
      "decoder_start_token_id": null,
      "max_length": 20,
      "min_length": 0,
      "do_sample": false,
      "early_stopping": false,
      "num_beams": 1,
      "temperature": 1.0,
      "top_k": 50,
      "top_p": 1.0,
      "typical_p": 1.0,
      "repetition_penalty": 1.0,
      "length_penalty": 1.0,
      "no_repeat_ngram_size": 0,
      "encoder_no_repeat_ngram_size": 0,
      "bad_words_ids": null,
      "num_return_sequences": 1,
      "output_scores": false,
      "return_dict_in_generate": false,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "remove_invalid_values": false,
      "exponential_decay_length_penalty": null,
      "suppress_tokens": null,
      "begin_suppress_tokens": null,
      "num_beam_groups": 1,
      "diversity_penalty": 0.0,
      "_name_or_path": "",
      "head_dim": 128,
      "model_type": "qwen3",
      "tf_legacy_loss": false,
      "use_bfloat16": false,
      "qk_norm": true,
      "layer_module": "Qwen3DecoderLayer",
      "output_attentions": false
    },
    "attn_implementation": "flash_attention_2",
    "output_attentions": false
  },
  "vit_config": {
    "return_dict": true,
    "output_hidden_states": false,
    "torchscript": false,
    "dtype": "bfloat16",
    "pruned_heads": {},
    "tie_word_embeddings": true,
    "chunk_size_feed_forward": 0,
    "is_encoder_decoder": false,
    "is_decoder": false,
    "cross_attention_hidden_size": null,
    "add_cross_attention": false,
    "tie_encoder_decoder": false,
    "architectures": [
      "InternVisionModel"
    ],
    "finetuning_task": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "task_specific_params": null,
    "problem_type": null,
    "tokenizer_class": null,
    "prefix": null,
    "bos_token_id": null,
    "pad_token_id": null,
    "eos_token_id": null,
    "sep_token_id": null,
    "decoder_start_token_id": null,
    "max_length": 20,
    "min_length": 0,
    "do_sample": false,
    "early_stopping": false,
    "num_beams": 1,
    "temperature": 1.0,
    "top_k": 50,
    "top_p": 1.0,
    "typical_p": 1.0,
    "repetition_penalty": 1.0,
    "length_penalty": 1.0,
    "no_repeat_ngram_size": 0,
    "encoder_no_repeat_ngram_size": 0,
    "bad_words_ids": null,
    "num_return_sequences": 1,
    "output_scores": false,
    "return_dict_in_generate": false,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "remove_invalid_values": false,
    "exponential_decay_length_penalty": null,
    "suppress_tokens": null,
    "begin_suppress_tokens": null,
    "num_beam_groups": 1,
    "diversity_penalty": 0.0,
    "_name_or_path": "",
    "auto_map": {
      "AutoConfig": "configuration_intern_vit.InternVisionConfig",
      "AutoModel": "modeling_intern_vit.InternVisionModel"
    },
    "model_type": "intern_vit_6b",
    "use_fa3": false,
    "tf_legacy_loss": false,
    "use_bfloat16": false,
    "hidden_size": 1024,
    "intermediate_size": 4096,
    "dropout": 0.0,
    "drop_path_rate": 0.0,
    "num_hidden_layers": 24,
    "num_attention_heads": 16,
    "num_channels": 3,
    "patch_size": 14,
    "image_size": 224,
    "initializer_range": 0.02,
    "initializer_factor": 1.0,
    "attention_dropout": 0.0,
    "layer_norm_eps": 1e-06,
    "hidden_act": "gelu",
    "norm_type": "layer_norm",
    "qkv_bias": true,
    "qk_normalization": false,
    "use_flash_attn": true,
    "select_layer": -1,
    "downsample_ratio": 0.5,
    "output_attentions": false
  },
  "connector_arch": "internvl_connector",
  "template": "being_h0",
  "select_layer": -1,
  "force_image_size": 224,
  "downsample_ratio": 0.5,
  "action_chunk_length": 16,
  "loss_func": "l1",
  "gen_action_type": "prop_hidden",
  "layer_select_for_action": -1,
  "action_token_num": 16,
  "learnable_action_query": false,
  "prompt_template": "long",
  "use_expert": true,
  "use_flow_matching": true,
  "attn_mode": "causal",
  "max_num_embodiments": 32,
  "noise_beta_alpha": 1.5,
  "noise_beta_beta": 1.0,
  "num_timestep_buckets": 1000,
  "noise_s": 0.999,
  "num_inference_timesteps": 4,
  "model_type": "beingh",
  "output_attentions": false
}