{ "type": "being_h05", "n_obs_steps": 1, "input_features": { "observation.images.robot0_agentview_left": { "type": "VISUAL", "shape": [ 3, 224, 224 ] }, "observation.images.robot0_agentview_right": { "type": "VISUAL", "shape": [ 3, 224, 224 ] }, "observation.images.robot0_eye_in_hand": { "type": "VISUAL", "shape": [ 3, 224, 224 ] }, "observation.state.eef_position": { "type": "STATE", "shape": [ 3 ] }, "observation.state.eef_rotation": { "type": "STATE", "shape": [ 3 ] }, "observation.state.gripper_qpos": { "type": "STATE", "shape": [ 2 ] }, "observation.state.base_position": { "type": "STATE", "shape": [ 3 ] }, "observation.state.base_rotation": { "type": "STATE", "shape": [ 3 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 12 ] } }, "device": "cuda", "use_amp": false, "use_peft": false, "push_to_hub": true, "repo_id": null, "private": null, "tags": null, "license": null, "pretrained_path": null, "pretrained_revision": null, "author_model_id": "BeingBeyond/Being-H05-2B", "author_config": { "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": [ "BeingH" ], "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_vlln": 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": "internlm2-chat", "select_layer": -1, "force_image_size": 224, "downsample_ratio": 0.5, "unified_state_dim": 200, "unified_action_dim": 200, "max_action_chunk_length": 16, "prompt_template": "long", "use_expert": true, "use_flow_matching": true, "filter_loss_proportion": 0.0, "motion_as_text": false, "pred_motion_continuous": false, "pred_motion_discrete": "none", "action_context_mode": "discrete", "motion_vocab_size": 8192, "motion_block_size": 128, "max_motion_chunk_length": 256, "latent_type": "simple", "use_latent_vision": false, "use_latent_loss": false, "output_num_latents": 32, "use_latent_predictor": false, "latent_encoder_name": "dinov2", "latent_dim": 256, "perceiver_num_latents": 64, "tune_latent_vit": false, "lat_enc_layer": -1, "lat_emb_layer": -1, "ema_decay": 0.999, "num_perceiver_layers": 2, "num_perceiver_heads": 8, "num_output_layers": 2, "num_output_heads": 8, "temporal_length": 2, "perceiver_dropout": 0.0, "lambda_latent": 0.8, "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, "use_mpg": true, "mpg_lambda": 0.0, "mpg_num_projections": 32, "mpg_refinement_iters": 1, "mpg_gate_temperature": 2.0, "mpg_use_stop_gradient": true, "action_chunk_length": 16, "action_token_num": 16 }, "tokenizer_name": "BeingBeyond/Being-H05-2B", "tokenizer_revision": "bb31ffcf7d67a8d5ec82d715d5e1678581ef6374", "embodiment": "robocasa_human", "embodiment_id": 31, "image_keys": [ "observation.images.robot0_agentview_left", "observation.images.robot0_agentview_right", "observation.images.robot0_eye_in_hand" ], "image_size": 224, "unified_state_dim": 200, "unified_action_dim": 200, "chunk_size": 16, "n_action_steps": 8, "num_inference_steps": 4, "prompt_template": "According to the instruction '{task_description}', what's the micro-step actions in the next {k} steps?", "metadata": {}, "optimizer_lr": 2e-05, "optimizer_weight_decay": 0.0, "scheduler_warmup_steps": 1000, "scheduler_decay_steps": 100000, "normalization_mapping": { "VISUAL": "IDENTITY", "STATE": "IDENTITY", "ACTION": "IDENTITY" } }