Llama

🔧🔗https://github.com/modelscope/ms-swift

SWIFT (Scalable lightWeight Infrastructure for Fine-Tuning) Use PEFT or Full-parameter to finetune 400+ LLMs or 100+ MLLMs.

yzma

https://github.com/hybridgroup/yzma Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration.

https://github.com/Mozilla-Ocho/llamafile Distribute and run LLMs with a single file. llamafile.ai

🔧🔗https://github.com/hiyouga/LLaMA-Factory Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Easy Edit

🔧🔗https://github.com/zjunlp/EasyEdit [ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

llama server

🔧🔗https://github.com/maragudk/llama-server A simple layer on top of ghcr.io/ggml-org/llama.cpp:server to load GGUF models from assets.maragu.dev at runtime.

🔧🔗https://github.com/andrewkchan/yalm

Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

https://github.com/distantmagic/structured Extracts structured data from unstructured input. Programming language agnostic. Uses llama.cpp