Codebase for Instruction Following without Instruction Tuning

Making LLaVA Tiny via MoE-Knowledge Distillation

Model components of the Llama Stack APIs

Model2Vec: Distill a Small Fast Model from any Sentence Transformer

An acceleration library that supports arbitrary bit-width combinatorial quantization operations

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

AI for all: Build the large graph of the language models

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

Official implementation of paper "On the Diagram of Thought" (https://arxiv.org/abs/2409.10038)

800,000 step-level correctness labels on LLM solutions to MATH problems

This project demonstrates a basic chain-of-thought interaction with any LLM (Large Language Model)

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.

Repo for for paper "AgentRE: An Agent-Based Framework for Navigating Complex Information Landscapes in Relation Extraction".

This project aims to implements quiet_star algoithm

A comprehensive survey on Internal Consistency and Self-Feedback in Large Language Models.

aider is AI pair programming in your terminal

The official repository of our survey paper: "Towards a Unified View of Preference Learning for Large Language Models: A Survey"

[EMNLP Findings 2024] MobileQuant: Mobile-friendly Quantization for On-device Language Models

Implementation of the Quiet-STAR paper (https://arxiv.org/pdf/2403.09629.pdf)

Code for Quiet-STaR

【大模型】3小时完全从0训练一个仅有26M的小参数GPT，最低仅需2G显卡即可推理训练！