{ "_commit_hash": null, "_name_or_path": "/data/ckpts/shimodi/pretrain_models/GO-1", "action_chunk_size": 30, "action_config": { "_attn_implementation_autoset": true, "_name_or_path": "", "action_chunk_size": 30, "action_dim": 16, "add_cross_attention": false, "architectures": [ "ActionExpertModel" ], "attn_implementation": "eager", "auto_map": { "AutoConfig": "configuration_action_expert.ActionExpertConfig", "AutoModel": "modeling_action_expert.ActionExpertModel" }, "bad_words_ids": null, "begin_suppress_tokens": null, "bias": false, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "head_dim": 64, "hidden_act": "silu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "input_hidden_size": 2048, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "min_length": 0, "model_type": "action_expert", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 2, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 2.0, "type": "dynamic" }, "rope_theta": 1000000, "sep_token_id": null, "state_dim": 16, "state_token_num": 3, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.46.3", "typical_p": 1.0, "use_bfloat16": true, "use_cache": true, "use_flash_attn": false }, "architectures": [ "GO1Model" ], "auto_map": { "AutoConfig": "configuration_go1.GO1ModelConfig", "AutoModel": "modeling_go1.GO1Model", "AutoModelForCausalLM": "modeling_internlm2_go1.py.InternLM2ForCausalLMGO1" }, "downsample_ratio": 0.5, "dynamic_image_size": false, "force_image_size": 448, "img_context_token_id": 92546, "latent_action_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "action_dim": 1, "action_horizon": 30, "add_cross_attention": false, "architectures": null, "attn_implementation": "eager", "bad_words_ids": null, "begin_suppress_tokens": null, "bias": false, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diffusion": false, "discrete": true, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "enable_act_training": true, "enable_ntp_training": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "final_use_diffusion": true, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "head_dim": 64, "hidden_act": "silu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "img_context_token_id": 92546, "initializer_range": 0.02, "input_hidden_size": 2048, "intermediate_size": 2048, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "llm_stop_token_ids": 92542, "mask_vision_head_prob": 0.0, "mask_vision_wrist_prob": 0.0, "max_length": 20, "max_position_embeddings": 2048, "min_length": 0, "model_type": "intermidiate_action_expert", "no_repeat_ngram_size": 0, "ntp_loss_weight": 0.1, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000, "sep_token_id": null, "state_token_num": 0, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.46.3", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 32 }, "latent_planner_config": { "_attn_implementation_autoset": false, "_name_or_path": "", "action_dim": 1, "add_cross_attention": false, "architectures": null, "attn_implementation": "eager", "bad_words_ids": null, "begin_suppress_tokens": null, "bias": false, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "head_dim": 64, "hidden_act": "silu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "input_hidden_size": 2048, "intermediate_size": 2048, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 2048, "min_length": 0, "model_type": "intermidiate_action_expert", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000, "sep_token_id": null, "state_token_num": 0, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "transformers_version": "4.46.3", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 32 }, "latent_planning": true, "llm_config": { "_attn_implementation_autoset": true, "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternLM2ForCausalLMGO1" ], "attn_implementation": "flash_attention_2", "auto_map": { "AutoConfig": "configuration_internlm2.InternLM2Config", "AutoModel": "modeling_internlm2_go1.InternLM2ForCausalLMGO1", "AutoModelForCausalLM": "modeling_internlm2_go1.py.InternLM2ForCausalLMGO1" }, "bad_words_ids": null, "begin_suppress_tokens": null, "bias": false, "bos_token_id": 1, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 8192, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "min_length": 0, "model_type": "internlm2", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 2, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 2.0, "type": "dynamic" }, "rope_theta": 1000000, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.46.3", "typical_p": 1.0, "use_bfloat16": true, "use_cache": true, "vocab_size": 92553 }, "max_dynamic_patch": 6, "min_dynamic_patch": 1, "model_type": "go1", "noise_scheduler_config": { "beta_schedule": "squaredcos_cap_v2", "clip_sample": false, "num_inference_timesteps": 5, "num_train_timesteps": 1000, "prediction_type": "sample" }, "norm": false, "pad2square": false, "pad_token_id": 2, "ps_version": "v2", "select_layer": -1, "template": "internlm2-chat", "torch_dtype": "bfloat16", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": false, "vision_config": { "_attn_implementation_autoset": true, "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.1, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.46.3", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": true } }