Robotics
Transformers
Safetensors
English
prts_qwen3_vl
image-feature-extraction
vision-language-action
vla
libero
qwen3-vl
prts
custom_code
Instructions to use TeleEmbodied/PRTS-4B-LIBERO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TeleEmbodied/PRTS-4B-LIBERO with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TeleEmbodied/PRTS-4B-LIBERO", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "action_chunk_size": 20, | |
| "action_expert_config": { | |
| "action_end_token_id": null, | |
| "action_start_token_id": 151669, | |
| "action_token_id": 151670, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "crl_goal_repr_token_id": 151672, | |
| "crl_obs_repr_token_id": 151673, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1280, | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2432, | |
| "max_position_embeddings": 262144, | |
| "model_type": "prts_qwen3_vl_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 5000000, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "video_token_id": 151656, | |
| "vision_start_token_id": 151652, | |
| "vocab_size": 153722 | |
| }, | |
| "action_start_token_id": 151669, | |
| "architectures": [ | |
| "PRTS_Qwen3VL" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_prts_qwen3_vl.PRTS_FlowMatchingConfig_Qwen3VL", | |
| "AutoModel": "modeling_prts_qwen3_vl.PRTS_Qwen3VL" | |
| }, | |
| "crl_embed_dim": 256, | |
| "crl_encoder_init_w": 0.001, | |
| "crl_goal_repr_token_id": 151672, | |
| "crl_logsumexp_reg_weight": 0.0, | |
| "crl_loss_weight": 0.0, | |
| "crl_obs_repr_token_id": 151673, | |
| "crl_repr_norm": true, | |
| "dit_action_head_config": { | |
| "add_pos_embed": true, | |
| "attend_text_every_n_blocks": 2, | |
| "attention_head_dim": 48, | |
| "attn_implementation": "sdpa", | |
| "dropout": 0.2, | |
| "final_dropout": true, | |
| "interleave_self_attention": true, | |
| "mlp_mult": 4, | |
| "noise_beta_alpha": 1.5, | |
| "noise_beta_beta": 1.0, | |
| "noise_s": 0.999, | |
| "norm_type": "ada_norm", | |
| "num_attention_heads": 32, | |
| "num_layers": 16, | |
| "num_timestep_buckets": 1000, | |
| "output_dim": 1024, | |
| "use_alternate_vl_dit": true, | |
| "use_mot_action_expert": true | |
| }, | |
| "dtype": "bfloat16", | |
| "embodiment_tag": "libero_panda", | |
| "flow_matching_action_loss_weight": 1.0, | |
| "flow_matching_sub_goal_loss_weight": 0.0, | |
| "image_token_id": 151655, | |
| "label2id": null, | |
| "max_action_dim": 32, | |
| "model_type": "prts_qwen3_vl", | |
| "num_denoise_steps": 5, | |
| "pad_token_id": 151643, | |
| "text_config": { | |
| "action_end_token_id": null, | |
| "action_start_token_id": 151669, | |
| "action_token_id": 151670, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "crl_goal_repr_token_id": 151672, | |
| "crl_obs_repr_token_id": 151673, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9728, | |
| "max_position_embeddings": 262144, | |
| "model_type": "prts_qwen3_vl_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 5000000, | |
| "tie_word_embeddings": true, | |
| "use_cache": false, | |
| "video_token_id": 151656, | |
| "vision_start_token_id": 151652, | |
| "vocab_size": 153722 | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "4.57.3", | |
| "use_cache": true, | |
| "use_fast_action_tokenizer": true, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [ | |
| 5, | |
| 11, | |
| 17 | |
| ], | |
| "depth": 24, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1024, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "model_type": "qwen3_vl", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 2560, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652, | |
| "vocab_size": 153722 | |
| } | |