https://github.com/falconlee236/llama-3.1-finetuned-with-lora-using-koalpaca
https://github.com/falconlee236/llama-3.1-finetuned-with-lora-using-koalpaca
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/falconlee236/llama-3.1-finetuned-with-lora-using-koalpaca
- Owner: falconlee236
- License: apache-2.0
- Created: 2025-01-05T12:46:32.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-02-13T06:14:18.000Z (4 months ago)
- Last Synced: 2025-02-13T07:24:11.565Z (4 months ago)
- Language: Python
- Size: 72.7 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Llama-3.1-Finetuned-with-LoRA-using-KoAlpaca
```
pyenv virtualenv 3.12.8 llama3.1-lora-koalpaca
```# reference
https://huggingface.co/docs/transformers/main/perf_train_gpu_one#using--acceleratehttps://huggingface.co/docs/transformers/main/perf_train_gpu_one