Instructions to use acl-srw-2024/llama-3-8b-instruct-4bit-SCB with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use acl-srw-2024/llama-3-8b-instruct-4bit-SCB with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "acl-srw-2024/llama-3-8b-instruct-4bit-SCB") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from acl-srw-2024/llama-3-8b-instruct-4bit-SCB: direct link, hf CLI and curl.
- Browser
- Download file 5.18 kB
-
https://huggingface.co/acl-srw-2024/llama-3-8b-instruct-4bit-SCB/resolve/main/training_args.bin
- Command line
-
hf download hf://acl-srw-2024/llama-3-8b-instruct-4bit-SCB/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/acl-srw-2024/llama-3-8b-instruct-4bit-SCB/resolve/main/training_args.bin
5.18 kB
- Xet hash:
- aed2d747ade99cc30b1d575bebf6fb0d0042e4d11c96fc68c3c1660ecd31420a
- Size of remote file:
- 5.18 kB
- SHA256:
- eb5e25161daf9a644fc6f424ef532a8a62def352287a10fe338a7cbc931e10b6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.