Code for "Learning to summarize from human feedback"

Code for the paper Fine-Tuning Language Models from Human Preferences

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

🦜🔗 The platform for reliable agents.

CLI platform to experiment with codegen. Precursor to: https://lovable.dev

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

A technical report on convolution arithmetic in the context of deep learning

Utilities intended for use with Llama models.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Examples and guides for using the OpenAI API

The official Python library for the OpenAI API

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

This is the code for the "How to Beat Pong Using Policy Gradients (LIVE)" by Siraj Raval on Youtube

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

Prefix-Tuning: Optimizing Continuous Prompts for Generation

Code for ALBEF: a new vision-language pre-training method

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.