llm code demo for begginer.
Welcome to the easy-llm Repository, a beginner-friendly platform that provides a comprehensive introduction to fine-tuning and inference of the LLM (Language Model) using practical code examples. Whether you're new to machine learning, natural language processing, or you're simply looking to expand your existing skills, this repository is an excellent starting point.
This repository contains a series of Python scripts that demonstrate how to fine-tune and perform inference on an LLM model. It includes:
- Fine-tuning a pre-trained LLM model on a custom dataset.
- Using a fine-tuned LLM model to generate predictions (inference).
- Detailed comments explaining each step of the process.
| Status | Base Model | Finetune Method | Dataset | Desc | Code |
|---|---|---|---|---|---|
| tiiuae/falcon-7b | QLoRA | heliosbrahma/mental_health_chatbot_dataset | finetune demo using lora with SFT | Code | |
| tiiuae/falcon-7b | QLoRA | - | inference demo using lora | Code | |
| tiiuae/falcon-7b | QLoRA | b-mc2/sql-create-context | finetune demo using lora | Code | |
| tiiuae/falcon-7b | QLoRA | - | Code |