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 MODEL_PROVENANCE.json from nvidia/Flora-TempSeg: direct link, hf CLI and curl.
- Browser
- Download file 542 Bytes
-
https://huggingface.co/nvidia/Flora-TempSeg/resolve/main/MODEL_PROVENANCE.json
- Command line
-
hf download hf://nvidia/Flora-TempSeg/MODEL_PROVENANCE.json
-
curl -L -o MODEL_PROVENANCE.json https://huggingface.co/nvidia/Flora-TempSeg/resolve/main/MODEL_PROVENANCE.json
542 Bytes
| { | |
| "schema_version": 2, | |
| "model": "Flora-segmenter-9B", | |
| "selected_step": 1300, | |
| "base_model": "Qwen/Qwen3.5-9B", | |
| "base_revision": "c202236235762e1c871ad0ccb60c8ee5ba337b9a", | |
| "format": "PEFT LoRA", | |
| "adapter_sha256": "1d80fe544e4cd1a7ff6b0ea4be71e988972408dab81d4c8af72e3a628739d6c3", | |
| "adapter_tensor_count": 496, | |
| "adapter_dtype": "F32", | |
| "lora_rank": 32, | |
| "lora_alpha": 64, | |
| "lora_scope": "language-model attention and MLP projections", | |
| "source_weights_modified": false, | |
| "adapter_config_public_base_binding_only": true | |
| } | |