Download experiment_cfg/final_model_config.json from RobotisSW/clean_table_distinguish_60k: direct link, hf CLI and curl.
- Browser
- Download file 1.76 kB
-
https://huggingface.co/RobotisSW/clean_table_distinguish_60k/resolve/main/experiment_cfg/final_model_config.json
- Command line
-
hf download hf://RobotisSW/clean_table_distinguish_60k/experiment_cfg/final_model_config.json
-
curl -L -o final_model_config.json https://huggingface.co/RobotisSW/clean_table_distinguish_60k/resolve/main/experiment_cfg/final_model_config.json
1.76 kB
| { | |
| "model_type": "Gr00tN1d7", | |
| "model_dtype": "bfloat16", | |
| "model_name": "nvidia/Cosmos-Reason2-2B", | |
| "backbone_model_type": "qwen", | |
| "model_revision": null, | |
| "tune_top_llm_layers": 0, | |
| "backbone_embedding_dim": 2048, | |
| "tune_llm": false, | |
| "tune_visual": false, | |
| "select_layer": 16, | |
| "reproject_vision": false, | |
| "use_flash_attention": true, | |
| "load_bf16": false, | |
| "backbone_trainable_params_fp32": true, | |
| "vision_weights_path": "/workspace/checkpoints/vision/paired-grounding-20260911/vision.safetensors", | |
| "attn_supervision_layers": null, | |
| "attn_supervision_weight": 0.5, | |
| "attn_supervision_mode": "vision", | |
| "attn_supervision_loss": "kl", | |
| "attn_supervision_margin": 0.9, | |
| "extra_augmentation_config": null, | |
| "apply_sincos_state_encoding": false, | |
| "use_percentiles": true, | |
| "use_relative_action": false, | |
| "max_state_dim": 132, | |
| "max_action_dim": 132, | |
| "action_horizon": 40, | |
| "hidden_size": 1024, | |
| "input_embedding_dim": 1536, | |
| "state_history_length": 1, | |
| "add_pos_embed": true, | |
| "attn_dropout": 0.2, | |
| "use_vlln": true, | |
| "max_seq_len": 1024, | |
| "use_alternate_vl_dit": true, | |
| "attend_text_every_n_blocks": 2, | |
| "diffusion_model_cfg": { | |
| "attention_head_dim": 48, | |
| "dropout": 0.2, | |
| "final_dropout": true, | |
| "interleave_self_attention": true, | |
| "norm_type": "ada_norm", | |
| "num_attention_heads": 32, | |
| "num_layers": 32, | |
| "output_dim": 1024, | |
| "positional_embeddings": null | |
| }, | |
| "num_inference_timesteps": 4, | |
| "noise_beta_alpha": 1.5, | |
| "noise_beta_beta": 1.0, | |
| "noise_s": 0.999, | |
| "num_timestep_buckets": 1000, | |
| "tune_projector": true, | |
| "tune_diffusion_model": true, | |
| "tune_vlln": true, | |
| "state_dropout_prob": 0.2, | |
| "exclude_state": false, | |
| "use_mean_std": false, | |
| "max_num_embodiments": 32 | |
| } |