liu-nlper
Follow
Stars
verl: Volcano Engine Reinforcement Learning for LLMs
Latest Advances on Long Chain-of-Thought Reasoning
Supercharge Your LLM Application Evaluations 🚀
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agent RL)
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
The source code for the schema filter (question + schema only)
AirLLM 70B inference with single 4GB GPU
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training
PICARD - Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models. PICARD is a ServiceNow Research project that was started at Element AI.
The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
Self-verification for LLMs.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
Fast and memory-efficient exact attention
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
The official Python library for the OpenAI API
A curated list of awesome data annotation tools
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Aligning pretrained language models with instruction data generated by themselves.