Stars
Hybrid-RAG is a hybrid Retrieval-Augmented Generation (RAG) model that leverages BERT for retrieving relevant documents and GPT-2 for generating more accurate responses.
A modular graph-based Retrieval-Augmented Generation (RAG) system
Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning"
Data and Model implementation for paper: FinDKG: Dynamic Knowledge Graph with Large Language Models for Global Finance
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
LLM Chatbot w/ Retrieval Augmented Generation using Llamaindex. It demonstrates how to impl. chunking, indexing, and source citation.
Build a chatbot powered by LlamaIndex that augments GPT 3.5 with the contents of the Streamlit docs (or your own data).
《计算机网络教程（高传善等编）》读书笔记，结合期末复习ppt提纲，为复旦大学大三上专业课《计算机网络》所写
Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。
It contains the assignments and projects of FDU-PRML spring 2023
Step-by-step Deep Leaning Tutorials on Apache Spark using BigDL
Accelerate LLM with low-bit (FP4 / INT4 / FP8 / INT8) optimizations using ipex-llm
Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…