https://github.com/nayeem01/fine-tuning-llama

Fine tuning llama3.1 8b with unsloth
https://github.com/nayeem01/fine-tuning-llama

fine-tuning langchain llm python

Last synced: about 1 month ago
JSON representation

Fine tuning llama3.1 8b with unsloth

• Host: GitHub
• URL: https://github.com/nayeem01/fine-tuning-llama
• Owner: nayeem01
• License: mit
• Created: 2024-09-05T03:20:17.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-09-29T05:59:06.000Z (about 2 months ago)
• Last Synced: 2024-10-07T18:31:08.000Z (about 1 month ago)
• Topics: fine-tuning, langchain, llm, python
• Language: Jupyter Notebook
• Homepage:
• Size: 271 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Fine-tuning-llama3.1_8b

- [x] Data Scraping news article

- [x] Data pre-processing

- [x] Fine tuning LLAMA3.1

### Output in ollama

![alt text](./assets/hasina_llama3.gif)

### HuggingFace repo

- https://huggingface.co/nayeem01/hasina_llama3_8b/tree/main

### NoteBooks Link

- Data processing - https://www.kaggle.com/code/nayeem000/data-pre-processing-for-llama3-1/edit

- Fine tuning llama3.1 (kaggle notebook) - https://www.kaggle.com/code/nayeem000/fine-tuning-llama3-1-unsloth-with-hasina-data/edit

- Google Colab - https://colab.research.google.com/drive/1nkbZSWjCeATmfUuGWfGyMz7GaGvsj6Zn

### How run locally with ollama

- wget -P /path/to/directory https://huggingface.co/nayeem01/hasina_llama3_8b/resolve/main/hasina_llama.Q4_K_M.gguf

- ollama create hasina_llama -f ./modelfile

- ollama run hasina_llama