FareedKhan-dev/train-tiny-llm

Train a 29M parameter GPT from Scratch

39
/ 100
Emerging

This project helps machine learning engineers or researchers build their own small, custom language models (LLMs) from scratch. You provide a large text corpus, and the project outputs a trained LLM capable of understanding and generating human-like text, along with a web interface to interact with it. It's designed for those who want to deeply understand and control the LLM development process, from tokenization to fine-tuning.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher who wants to train a small, instruction-following language model tailored to specific data, rather than using a pre-existing large model.

Not ideal if you need a production-ready, highly capable LLM immediately without deep diving into its internal workings, or if you lack the computational resources (GPU, RAM) for training.

natural-language-processing machine-learning-engineering custom-ai-model-training conversational-ai
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

34

Forks

7

Language

Python

License

MIT

Last pushed

Mar 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/FareedKhan-dev/train-tiny-llm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.