Instructions to use nrishabh/llama3-8b-instruct-qlora-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nrishabh/llama3-8b-instruct-qlora-large with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("LoftQ/Meta-Llama-3-8B-Instruct-4bit-64rank") model = PeftModel.from_pretrained(base_model, "nrishabh/llama3-8b-instruct-qlora-large") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from nrishabh/llama3-8b-instruct-qlora-large: direct link, hf CLI and curl.
- Browser
- Download file 5.05 kB
-
https://huggingface.co/nrishabh/llama3-8b-instruct-qlora-large/resolve/main/training_args.bin
- Command line
-
hf download hf://nrishabh/llama3-8b-instruct-qlora-large/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/nrishabh/llama3-8b-instruct-qlora-large/resolve/main/training_args.bin
5.05 kB
- Xet hash:
- 9cdbe163f4768532a2e657184445420706865ef6caf427b311e4f84e4801959d
- Size of remote file:
- 5.05 kB
- SHA256:
- 1566104477e43dbd953449afb6f0974e2c7765e1042ea8d06d2a920964a1cde5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.