Instructions to use nvidia/Flora-TempSeg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nvidia/Flora-TempSeg with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-9B") model = PeftModel.from_pretrained(base_model, "nvidia/Flora-TempSeg") - Notebooks
- Google Colab
- Kaggle
Download batch_utils/config.py from nvidia/Flora-TempSeg: direct link, hf CLI and curl.
- Browser
- Download file 503 Bytes
-
https://huggingface.co/nvidia/Flora-TempSeg/resolve/refs%2Fpr%2F4/batch_utils/config.py
- Command line
-
hf download hf://nvidia/Flora-TempSeg@refs/pr/4/batch_utils/config.py
-
curl -L -o config.py https://huggingface.co/nvidia/Flora-TempSeg/resolve/refs%2Fpr%2F4/batch_utils/config.py
503 Bytes
| from pathlib import Path | |
| import json | |
| import os | |
| ROOT = Path(__file__).resolve().parent | |
| VENDOR = ROOT / 'vendor' | |
| MODELS = json.loads((ROOT / 'models.json').read_text()) | |
| MODEL_CACHE = Path(os.environ.get('FLORA_MODEL_CACHE', Path.home() / '.cache' / 'flora' / 'models')) | |
| MAX_DURATION_S = 120 | |
| MAX_UPLOAD_BYTES = 256 * 1024 * 1024 | |
| MAX_DIMENSION = 4096 | |
| MAX_FRAME_COUNT = 7200 | |
| PROFILE_POOLS = {'Human': 'human', 'Human actions': 'human', 'YAM': 'yam', 'Dex': 'dex', 'Tianji': 'tianji', 'Robot actions': 'yam'} | |