Robotics
Transformers
Safetensors
molmoact2
image-text-to-text
so100
so101
custom_code
8-bit precision
Instructions to use OpenRAL/rskill-molmoact2-so101-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenRAL/rskill-molmoact2-so101-nf4 with Transformers:
# Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("OpenRAL/rskill-molmoact2-so101-nf4", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "source_repo": "allenai/MolmoAct2-SO100_101", | |
| "source_revision": "152569fe57914d97be91055800035f54e250d009", | |
| "policy_class": "transformers:AutoModelForImageTextToText", | |
| "quantization": { | |
| "scheme": "nf4", | |
| "backend": "bitsandbytes", | |
| "compute_dtype": "bfloat16", | |
| "min_params_to_quantize": 4000000, | |
| "rule": "Linear modules with >=4_000_000 weight elements rewritten to bnb.nn.Linear4bit; smaller heads kept in compute_dtype (bfloat16).", | |
| "runtime_status": "loader-backed (install_prequantized_linears)" | |
| }, | |
| "dropped_state_entries": [] | |
| } |