Robotics
Transformers
Safetensors
minicpm_vla
feature-extraction
vision-language-action
embodied-ai
minicpm
manipulation
custom_code
Instructions to use openbmb/MiniCPM-RobotManip with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/MiniCPM-RobotManip with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("openbmb/MiniCPM-RobotManip", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "action_dim": 80, | |
| "action_head_dtype": "float32", | |
| "action_horizon": 30, | |
| "architectures": [ | |
| "MiniCPMV_VLA" | |
| ], | |
| "dtype": "bfloat16", | |
| "max_num_embodiments": 32, | |
| "model_type": "minicpm_vla", | |
| "num_inference_timesteps": 4, | |
| "state_dim": 80, | |
| "transformers_version": "5.7.0", | |
| "vlm_config": { | |
| "architectures": [ | |
| "MiniCPMV4_6ForConditionalGeneration" | |
| ], | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "downsample_mode": "16x", | |
| "drop_vision_last_layer": false, | |
| "dtype": null, | |
| "eos_token_id": 248044, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 1120, | |
| "image_token_id": 248056, | |
| "insert_layer_id": 6, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "merge_kernel_size": [ | |
| 2, | |
| 2 | |
| ], | |
| "merger_times": 1, | |
| "model_type": "minicpmv4_6", | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": null, | |
| "patch_size": 14, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "text_config": { | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "dtype": null, | |
| "eos_token_id": null, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3584, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 16, | |
| "linear_value_head_dim": 128, | |
| "mamba_ssm_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_text", | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.25, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "vocab_size": 248094 | |
| }, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.7.0", | |
| "video_token_id": 248057, | |
| "vision_config": { | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "chunk_size_feed_forward": 0, | |
| "dtype": null, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 980, | |
| "insert_layer_id": 6, | |
| "intermediate_size": 4304, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-06, | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "patch_size": 14, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "window_kernel_size": [ | |
| 2, | |
| 2 | |
| ] | |
| } | |
| }, | |
| "vlm_dtype": "bfloat16", | |
| "auto_map": { | |
| "AutoConfig": "configuration_minicpm_vla.MiniCPMVLAConfig", | |
| "AutoModel": "modeling_minicpm_vla.MiniCPMV_VLA" | |
| } | |
| } | |