Instructions to use 4daJ/llama2_SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use 4daJ/llama2_SFT with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/data/lizongyue/llm_factory/model/meta-llama/Llama-2-7b-chat-hf") model = PeftModel.from_pretrained(base_model, "4daJ/llama2_SFT") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from 4daJ/llama2_SFT: direct link, hf CLI and curl.
- Browser
- Download file 16.8 MB
-
https://huggingface.co/4daJ/llama2_SFT/resolve/main/adapter_model.bin
- Command line
-
hf download hf://4daJ/llama2_SFT/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/4daJ/llama2_SFT/resolve/main/adapter_model.bin
16.8 MB
- Xet hash:
- 417121997a9581e8942ecc073127cf9cca56c7d5852b9fed337f6d6faecdb761
- Size of remote file:
- 16.8 MB
- SHA256:
- 233c602a04a16f836c6e019663b52c86f640b40e3e092b8c2987622fb304dc51
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.