| { |
| "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_dig_flow": false, |
| "dig_flow_num_projections": 32, |
| "dig_flow_lambda": 0.1, |
| "dig_flow_use_stop_gradient": true, |
| "dig_flow_refinement_iters": 1, |
| "dig_flow_gate_temperature": 2.0, |
| "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", |
| "freeze_und": false, |
| "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", |
| "freeze_und": false, |
| "moe_layer_ids": [], |
| "num_experts": 5, |
| "num_experts_per_tok": 2, |
| "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": "internvl2_5", |
| "select_layer": -1, |
| "force_image_size": 224, |
| "downsample_ratio": 0.5, |
| "max_state_dim": 64, |
| "max_action_dim": 32, |
| "action_chunk_length": 15, |
| "loss_func": "l1", |
| "gen_action_type": "prop_hidden", |
| "layer_select_for_action": -1, |
| "action_token_num": 15, |
| "k_token_one_action": 1, |
| "learnable_action_query": false, |
| "bid_attn": false, |
| "use_features": "raw_features", |
| "prompt_template": "long", |
| "use_expert": true, |
| "use_flow_matching": true, |
| "attn_mode": "causal", |
| "prop_context_token_id": 151684, |
| "action_token_ids": [ |
| 151685, |
| 151686, |
| 151687, |
| 151688, |
| 151689, |
| 151690, |
| 151691, |
| 151692, |
| 151693, |
| 151694, |
| 151695, |
| 151696, |
| 151697, |
| 151698, |
| 151699, |
| 151700 |
| ], |
| "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, |
| "action_head_cfg": { |
| "action_dim": 32, |
| "action_horizon": 15, |
| "add_pos_embed": true, |
| "backbone_embedding_dim": 2048, |
| "diffusion_model_cfg": { |
| "attention_head_dim": 48, |
| "cross_attention_dim": 2048, |
| "dropout": 0.2, |
| "final_dropout": true, |
| "interleave_self_attention": true, |
| "norm_type": "ada_norm", |
| "num_attention_heads": 32, |
| "num_layers": 16, |
| "output_dim": 1024 |
| }, |
| "hidden_size": 1024, |
| "input_embedding_dim": 1536, |
| "max_state_dim": 64, |
| "max_action_dim": 32, |
| "model_dtype": "float32", |
| "noise_beta_alpha": 1.5, |
| "noise_beta_beta": 1.0, |
| "noise_s": 0.999, |
| "num_inference_timesteps": 4, |
| "num_target_vision_tokens": 32, |
| "num_timestep_buckets": 1000, |
| "max_num_embodiments": 1, |
| "use_vlln": true, |
| "vl_self_attention_cfg": { |
| "attention_head_dim": 64, |
| "dropout": 0.2, |
| "final_dropout": true, |
| "num_attention_heads": 32, |
| "num_layers": 4 |
| } |
| }, |
| "img_context_token_id": 151671, |
| "model_type": "beingh", |
| "output_attentions": false |
| } |
