chelsea0x3b/llama-dfdx

LLaMa 7b with CUDA acceleration implemented in rust. Minimal GPU memory needed!

34
/ 100
Emerging

This tool allows developers to integrate the LLaMa 7b large language model directly into their Rust applications. It takes the LLaMa model weights and a text prompt as input, and outputs generated text or engaging in a chat-like interaction. It is designed for Rust developers who need to embed powerful language generation capabilities directly within their software.

111 stars. No commits in the last 6 months.

Use this if you are a Rust developer looking to embed a performant LLaMa 7b language model, leveraging CUDA for acceleration, directly within your application.

Not ideal if you are not a Rust developer or do not have access to a CUDA-compatible GPU, as CPU performance without CUDA is not supported.

Rust-development NLP-application-development AI-model-integration language-model-deployment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

111

Forks

6

Language

Rust

License

MIT

Last pushed

Jul 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/chelsea0x3b/llama-dfdx"

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