tomsanbear/bitnet-rs
Implementing the BitNet model in Rust
This project helps machine learning engineers and researchers explore an alternative, experimental approach to building transformer models. It takes pre-tokenized text datasets as input and outputs a trained BitNet model, which can then be used to generate text based on prompts. It's designed for those who work with model development and want to experiment with novel architectures.
No commits in the last 6 months.
Use this if you are a machine learning engineer interested in implementing and experimenting with the BitNet transformer architecture in Rust using Candle.
Not ideal if you need a production-ready, highly accurate text generation model for immediate use, as this is an experimental implementation with known issues in output coherence.
Stars
46
Forks
2
Language
Rust
License
MIT
Category
Last pushed
Apr 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/tomsanbear/bitnet-rs"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huawei-csl/SINQ
Welcome to the official repository of SINQ! A novel, fast and high-quality quantization method...
SILX-LABS/QUASAR-SUBNET
QUASAR is a long-context foundation model and decentralized evaluation subnet built on Bittensor,
stackblogger/bitnet.js
BitNet.Js - A node.js implementation of the microsoft bitnet.cpp inference framework.
m96-chan/0xBitNet
Run BitNet b1.58 ternary LLMs with WebGPU — in browsers and native apps
AnswerDotAI/cold-compress
Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking...