Port of Facebook's LLaMA model in C/C++
Run Local LLMs on Any Device. Open-source
Integrate cutting-edge LLM technology quickly and easily into your app
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
Ongoing research training transformer models at scale
Python bindings for the Transformer models implemented in C/C++
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
Leveraging BERT and c-TF-IDF to create easily interpretable topics
Implements a reference architecture for creating information systems