Instructions to use Jeesup/llama32-3B-rte-bf16-lora-seed44 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Jeesup/llama32-3B-rte-bf16-lora-seed44 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B") model = PeftModel.from_pretrained(base_model, "Jeesup/llama32-3B-rte-bf16-lora-seed44") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.safetensors from Jeesup/llama32-3B-rte-bf16-lora-seed44: direct link, hf CLI and curl.
- Browser
- Download file 36.7 MB
-
https://huggingface.co/Jeesup/llama32-3B-rte-bf16-lora-seed44/resolve/main/adapter_model.safetensors
- Command line
-
hf download hf://Jeesup/llama32-3B-rte-bf16-lora-seed44/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/Jeesup/llama32-3B-rte-bf16-lora-seed44/resolve/main/adapter_model.safetensors
36.7 MB
- Xet hash:
- da4ac7f124acb9cb1522a88f7177a52b811009c701be44fc52a1445d237cf845
- Size of remote file:
- 36.7 MB
- SHA256:
- 574ba801b706dc35394d4ba18990378684a2e5e1a8842a12e55c601f29ea7123
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.