Starred repositories
经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新
👩🏿💻👨🏾💻👩🏼💻👨🏽💻👩🏻💻中国独立开发者项目列表 -- 分享大家都在做什么
A LLM training and evaluation benchmark for credit scoring
A real world full-stack application using LlamaIndex
Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥
Code for the paper `Text Classification via Large Language Models`.
A free and unlimited API for Google Translate 💵🚫
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
🦜🔗 Build context-aware reasoning applications
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)
Integrating ONgDB database into langchain ecosystem
A series of large language models developed by Baichuan Intelligent Technology
Open standard for machine learning interoperability
PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!
Production-ready platform for agentic workflow development.
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".