Run Local LLMs on Any Device. Open-source
Port of Facebook's LLaMA model in C/C++
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
Minimal C implementation for training and inferring Llama 2
Open-source large language model family from Tencent Hunyuan
Integrate cutting-edge LLM technology quickly and easily into your app
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
Ongoing research training transformer models at scale
Leveraging BERT and c-TF-IDF to create easily interpretable topics
Python bindings for the Transformer models implemented in C/C++
Implements a reference architecture for creating information systems