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
File size: 569 Bytes
e01c114 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | {
"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": []
} |