Video-Text-to-Text
Transformers
Safetensors
qwen3_5
image-text-to-text
robotics
reward-model
vlm
gr00t
system-2
Instructions to use nvidia/Flora-Rewarder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/Flora-Rewarder with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("nvidia/Flora-Rewarder") model = AutoModelForMultimodalLM.from_pretrained("nvidia/Flora-Rewarder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
6 days ago
-
Add Flora inference examples
Omar LVerified signatureAdds the ten batch_utils inference files from flora-share/Flora-Rewarder-Release-Infer@1f1040b56a03845c93108a83bc3c4cb38761fb4c for terminal, dense, and rubric reward scoring. All existing repository files remain unchanged. Python syntax, template equivalence, model-asset identity, and lightweight dense-stitch checks passed; CUDA inference was not run. Upstream rubric behavior is preserved: out-of-set/non-finite scores can be accepted or clamped, and prompt score formatting can lose precision. These known limitations need review before merge.52f830a