tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Fine-Tuning Mistral-7b for Real-World Chatbot Applications Using Axolotl (Lora used) (#1155)

Browse Source 
* Mistral-7b finetune example using axolotl with code,config,data

* Corrected the path for huggingface dataset

* Update data.jsonl

* chore: lint

---------

Co-authored-by: twenty8th <twenty8th@users.noreply.github.com>
Co-authored-by: Wing Lian <wing.lian@gmail.com>
This commit is contained in:
Tilemachos Chatzipapas
2024-01-23 14:32:21 +02:00
committed by GitHub
parent 9135b9e2aa
commit cc250391a0
5 changed files with 1070 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/mistral/Mistral-7b-example/README.md Normal file
View File

@@ -0,0 +1,12 @@
# Description
This repository presents an in-depth guide for fine-tuning Mistral-7b or any other compatible model using Axolotl, tailored specifically for chatbot development. It streamlines the process of fine-tuning and uploading the enhanced model to HuggingFace 🤗, thereby serving as an invaluable tool for developers in the AI and chatbot domain.
**What’s Inside:**
Beginner-Friendly Instructions: Comprehensive steps to guide you through fine-tuning your chosen model, including details on the data structure (jsonl), configuration, and the code itself.
Hardware Utilized: For reference, the fine-tuning in this guide was performed using 4x NVIDIA GeForce RTX 3090 (rented 2.1.2-cuda12.1-cudnn8-devel).
**Uploading to HuggingFace 🤗:**
To upload your fine-tuned model to Hugging Face, include the following files:
![Screenshot 2024-01-19 213932](https://github.com/OpenAccess-AI-Collective/axolotl/assets/138583191/d660eb84-2d76-46a1-9846-cf0aeb3006d9)