tpoisonooo

4 bits quantization of LLaMA using GPTQ

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

Netease Youdao's open-source embedding and reranker models for RAG products.

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

dabnn is an accelerated binary neural networks inference framework for mobile platform