Instructions to use Expert68/llama2_peft_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Expert68/llama2_peft_v3 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/root/lm_weights/llama2_13b_hf") model = PeftModel.from_pretrained(base_model, "Expert68/llama2_peft_v3") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from Expert68/llama2_peft_v3: direct link, hf CLI and curl.
- Browser
- Download file 210 MB
-
https://huggingface.co/Expert68/llama2_peft_v3/resolve/main/adapter_model.bin
- Command line
-
hf download hf://Expert68/llama2_peft_v3/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/Expert68/llama2_peft_v3/resolve/main/adapter_model.bin
210 MB
- Xet hash:
- 531d3a2ceb7b38175302e79f0e1d1e7bf9d1c1586fa82e7873e574edb90d0daa
- Size of remote file:
- 210 MB
- SHA256:
- 50f0cb2c70af5ab8e70cd683e7e1058674235c8c5dc69feb6211cb441c58409c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.