Robotics
Transformers
Safetensors
English
molmoact2
image-text-to-text
OpenRAL
rskill
vision-language-action
nf4
4-bit precision
franka_panda
vla
libero
manipulation
custom_code
8-bit precision
Instructions to use OpenRAL/rskill-molmoact2-franka_panda-libero_spatial-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenRAL/rskill-molmoact2-franka_panda-libero_spatial-nf4 with Transformers:
# Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("OpenRAL/rskill-molmoact2-franka_panda-libero_spatial-nf4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 566 Bytes
60e450f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | {
"source_repo": "allenai/MolmoAct2-LIBERO",
"source_revision": "0d24a92bd1faf321ef497c3bbd5681af97c65aa2",
"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": []
} |