Instructions to use open-gigaai/GigaBrain-0.7-3.5B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use open-gigaai/GigaBrain-0.7-3.5B-Base with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("open-gigaai/GigaBrain-0.7-3.5B-Base", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "_class_name": "GigaBrain0Policy", | |
| "_diffusers_version": "0.34.0", | |
| "action_loss_vlm_gradient_weight": 0.1, | |
| "agent_pos_config": { | |
| "state": 32 | |
| }, | |
| "compact_language_logits": true, | |
| "crossdit_attention_head_dim": 64, | |
| "crossdit_num_target_vision_tokens": 32, | |
| "detach_history_frames": true, | |
| "enable_knowledge_insulation": true, | |
| "enable_learnable_traj_token": false, | |
| "enable_next_token_prediction": true, | |
| "expert_intermediate_size": null, | |
| "expert_type": "dual_stream", | |
| "fast_token_tail_skip_tokens": 128, | |
| "fast_token_tail_vocab_size": null, | |
| "fast_token_vocab_mode": "tail", | |
| "fast_vocab_size": 2048, | |
| "flow_action_horizon": 50, | |
| "gemma3_config_dict": null, | |
| "gemma3_expert_final_norm_ada": false, | |
| "gemma3_expert_full_attends_prefix": false, | |
| "gemma3_gate_self_mlp": true, | |
| "gemma4_config_dict": null, | |
| "gemma4_expert_cross_attend_shared_layers": false, | |
| "gemma4_expert_final_norm_ada": true, | |
| "gemma4_expert_full_attends_prefix": false, | |
| "has_action_expert": true, | |
| "language_loss_checkpoint": true, | |
| "language_loss_chunk_size": 0, | |
| "max_action_dim": 32, | |
| "max_state_dim": 32, | |
| "max_traj_dim": 4, | |
| "n_action_steps": 50, | |
| "num_embodiments": 8, | |
| "num_steps": 10, | |
| "num_traj_tokens": 10, | |
| "observation_memory_size": 1, | |
| "proj_width": 1024, | |
| "proj_with_mask": true, | |
| "propri_token_id": 257153, | |
| "qwen2_5_vl_config_dict": null, | |
| "qwen3_5_config_dict": null, | |
| "qwen3_vl_config_dict": null, | |
| "qwen3_vl_expert_adarms_base": false, | |
| "robomanip_attention_head_dim": 64, | |
| "robomanip_cross_attn_modality_alternating": true, | |
| "robomanip_ff_dim": null, | |
| "robomanip_num_layers": 10, | |
| "robomanip_num_query_tokens": 0, | |
| "state_hidden_size": 2048, | |
| "state_input_mode": "proprio_anchor", | |
| "temporal_attention_interval": 4, | |
| "traj_hidden_dim": 256, | |
| "use_cache": true, | |
| "vision_in_channels": 3, | |
| "vlm_hidden_size": 2304, | |
| "vlm_type": "paligemma2" | |
| } | |