Ömer Kaya's starred repositories
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
whisper.cpp
Port of OpenAI's Whisper model in C/C++
bark-with-voice-clone
🔊 Text-prompted Generative Audio Model - With the ability to clone voices
fsdp_qlora
Training LLMs with QLoRA + FSDP
dria-docker
All-in-one environment to use Dria, the collective knowledge for AI.
neural-tree
Tree-based indexes for neural-search
mlx-graphs
Graph Neural Network library made for Apple Silicon
graspologic
Python package for graph statistics
mlx-examples
Examples in the MLX framework
natural-instructions
Expanding natural instructions
opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
ollama-python
Ollama Python library
dria-python-client
Permissionless access to AI knowledge as a public good
RAGatouille
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.