How mshumer/gpt-llm-trainer works
This repository is a set of notebook-based workflows for turning a task description into a fine-tuned language model. The documented path is task description → generated examples and system message → formatted, split data → fine-tuning → inference. The notebooks offer Claude/LLaMA 2 and GPT-3.5 variants; the README also documents saving LLaMA models to Google Drive and using GPT-3.5 models through OpenAI. No notebook source excerpts were available, so links below reflect README-documented behavior only.
Main entry points: gpt_llm_trainer_v2,_with_GPT_3_5_Fine_Tuning.ipynb GPT-3.5 notebook · claude_llm_trainer.ipynb Example generation · One_Prompt___Fine_Tuned_LLaMA_2.ipynb LLaMA 2 notebook
Components 13
Dataset workflow
- Claude LLaMA notebook
claude_llm_trainer.ipynb - LLaMA 2 notebook
One_Prompt___Fine_Tuned_LLaMA_2.ipynb - GPT-3.5 notebook
gpt_llm_trainer_v2,_with_GPT_3_5_Fine_Tuning.ipynb - Example generation
claude_llm_trainer.ipynb - System message
claude_llm_trainer.ipynb - Format and split
One_Prompt___Fine_Tuned_LLaMA_2.ipynb
Models and inference
- Fine-tuning
One_Prompt___Fine_Tuned_LLaMA_2.ipynb - Inference
One_Prompt___Fine_Tuned_LLaMA_2.ipynb - Model storage
One_Prompt___Fine_Tuned_LLaMA_2.ipynb
External services
- OpenAI API
- Google Drive
- Claude 3 / GPT-4
Other components
- Task author
Connections 16
- Task author → Claude LLaMA notebook: sets task
README.md - Task author → LLaMA 2 notebook: sets task
README.md - Task author → GPT-3.5 notebook: sets task
README.md - Claude LLaMA notebook → Example generation: generates examples
README.md - LLaMA 2 notebook → Example generation: generates examples
README.md - GPT-3.5 notebook → Example generation: generates examples
README.md - Example generation → Claude 3 / GPT-4: uses models
README.md - Claude LLaMA notebook → System message: generates
README.md - LLaMA 2 notebook → Format and split: formats and splits
README.md - GPT-3.5 notebook → Format and split: formats and splits
README.md - Format and split → Fine-tuning: provides datasets
README.md - Fine-tuning → Inference: prepares model
README.md - GPT-3.5 notebook → OpenAI API: sets API key
README.md - Inference → OpenAI API: uses model API
README.md - Fine-tuning → Model storage: saves model
README.md - Model storage → Google Drive: stores in
README.md