Rust Llama2 Resources

The Natural Language Shell integrates GPT4 or local GGUF-formatted models directly into the terminal experience, allowing operators to describe their tasks in either POSIX commands or fluent human language

llama2.rs 🤗 This is a Rust implementation of Llama2 inference on CPU The goal is to be as fast as possible. It has the following features: Support fo

🦙🦙.🦀 An rust reimplementatin of https://github.com/karpathy/llama2.c. Run it This repo contains a tinystories15M in the testdata/ folder, you can r

llama2-rs LLaMA2 port for Rust inspired by llama2.c. TODOs: Implement loading of the model Implement forward pass Implement generation Implement token

summarize-cli Attempt to summarize text from stdin, using a large language model (locally and offline), to stdout. cargo build --release target/releas

llama2.rs Rust meets llama. A mimimal Rust implementation of karpathy's llama.c. Currently the code uses the 15M parameter model provided by Karpathy