brianberns/MinGptSharp
A F# .NET TorchSharp port of Andrej Karpathy's minGPT.
This is a tool for developers who want to experiment with or understand the core mechanics of how large language models like GPT are trained. It takes text data as input and produces a trained generative model that can predict the next word in a sequence. Developers working with .NET and F# interested in AI model training would use this.
No commits in the last 6 months.
Use this if you are a .NET/F# developer looking for a straightforward, minimal implementation of a GPT-style model for educational purposes or foundational experiments.
Not ideal if you need a production-ready, highly optimized, or feature-rich large language model for immediate application.
Stars
10
Forks
1
Language
F#
License
—
Category
Last pushed
Jul 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/brianberns/MinGptSharp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LowinLi/transformers-stream-generator
This is a text generation method which returns a generator, streaming out each token in...
ystemsrx/mini-nanoGPT
One-click training of your own GPT. Training a GPT has never been easier for beginners. /...
jaymody/picoGPT
An unnecessarily tiny implementation of GPT-2 in NumPy.
kyegomez/AttentionGrid
A network of attention mechanisms at your fingertips. Unleash the potential of attention...
kamalkraj/minGPT-TF
A minimal TF2 re-implementation of the OpenAI GPT training