Instructions to use Expert68/llama2_peft_v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Expert68/llama2_peft_v4 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_v4") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from Expert68/llama2_peft_v4: direct link, hf CLI and curl.
- Browser
- Download file 1 GB
-
https://huggingface.co/Expert68/llama2_peft_v4/resolve/main/adapter_model.bin
- Command line
-
hf download hf://Expert68/llama2_peft_v4/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/Expert68/llama2_peft_v4/resolve/main/adapter_model.bin
1 GB
- Xet hash:
- e1baa6523aa9b6cbd6fbaaec7e66abef36ae4866e68359cf9fbdd84ae903f0ff
- Size of remote file:
- 1 GB
- SHA256:
- 6d8041526767636b82871fed4fccd2848c44be7219cad2bc71284fd295511f67
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.