xinzhanguo/hellollm
pre train a new llm
This project helps machine learning engineers pre-train a new large language model (LLM) from scratch using custom textual data. You provide raw text files, and it produces a fine-tuned tokenizer and a new language model capable of generating text based on your input data's patterns and vocabulary. This tool is for developers building specialized conversational AI or text generation systems.
No commits in the last 6 months.
Use this if you need to create a brand-new large language model tailored specifically to your unique domain's text data, rather than adapting an existing general-purpose model.
Not ideal if you want to fine-tune an existing, pre-trained large language model, or if you don't have the technical expertise to set up and manage a deep learning training pipeline.
Stars
73
Forks
22
Language
Python
License
MIT
Category
Last pushed
Jan 16, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/xinzhanguo/hellollm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AI-Hypercomputer/maxtext
A simple, performant and scalable Jax LLM!
rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
mindspore-lab/mindnlp
MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless...
mosaicml/llm-foundry
LLM training code for Databricks foundation models
rickiepark/llm-from-scratch
<밑바닥부터 만들면서 공부하는 LLM>(길벗, 2025)의 코드 저장소