kreasof-ai/OpenFormer
A hackable library for running and fine-tuning modern transformer models on commodity and alternative GPUs, powered by tinygrad.
This is a library designed for machine learning engineers and researchers who want to train and run large language models (LLMs) without needing NVIDIA GPUs. It takes publicly available transformer model architectures and allows you to fine-tune them with your own data or use them for text generation on a variety of consumer-grade GPUs, including AMD, Intel, and Apple Silicon. The output is a specialized LLM model or generated text.
Use this if you are a machine learning engineer or researcher looking to experiment with, train, or fine-tune large language models efficiently on non-NVIDIA GPUs, especially for tasks requiring custom training rather than rapid text generation.
Not ideal if your primary need is ultra-fast, real-time text generation (inference) with large language models, as its current inference speed is slower compared to PyTorch-based implementations.
Stars
28
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kreasof-ai/OpenFormer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action