https://github.com/chandima2000/fine-tuned-llama2-llm-with-own-dataset

This is a basic illustration of how fine-tuning can perform to the LLM model using own data set.
https://github.com/chandima2000/fine-tuned-llama2-llm-with-own-dataset

finetuning-llms llama2-13b machine-learning python

Last synced: about 1 month ago
JSON representation

This is a basic illustration of how fine-tuning can perform to the LLM model using own data set.

• Host: GitHub
• URL: https://github.com/chandima2000/fine-tuned-llama2-llm-with-own-dataset
• Owner: chandima2000
• Created: 2024-06-13T09:41:27.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-06-13T09:59:16.000Z (6 months ago)
• Last Synced: 2024-11-17T09:15:57.970Z (about 1 month ago)
• Topics: finetuning-llms, llama2-13b, machine-learning, python
• Language: Jupyter Notebook
• Homepage:
• Size: 10.7 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# fine-tuned-LLM-model-own-dataset

- The Fine-tuned process is based on the `Nous-Hermes-Llama2-13b` Large Language Model.

- In this project, the LLM model is fine-tuned using the Gradient.ai platform.

- Nous-Hermes-Llama2-13b is a state-of-the-art language model fine-tuned on over 300,000 instructions. This model was fine-tuned by Nous Research, with Teknium and Emozilla leading the fine-tuning process and dataset curation, Redmond AI sponsoring the compute, and several other contributors.

- Here, I used a Python dictionary to import my own data set.

- Model is trained under 3 iterations.

- This is a basic illustration of how fine-tuning can perform to the LLM model using own data set.