The official repository of "Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint"

A large-scale, fine-grained, diverse preference dataset (and models).

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

SimPO: Simple Preference Optimization with a Reference-Free Reward

Reference implementation for DPO (Direct Preference Optimization)

The hub for EleutherAI's work on interpretability and learning dynamics

Achieving Efficient Alignment through Learned Correction

Code for M4LE: A Multi-Ability Multi-Range Multi-Task Multi-Domain Long-Context Evaluation Benchmark for Large Language Models

contrastive decoding

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

The official Meta Llama 3 GitHub site

DSPy: The framework for programming—not prompting—foundation models

Code for "Learning to Edit: Aligning LLMs with Knowledge Editing (ACL 2024)"

Code and data for "MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models"

Fast and memory-efficient exact attention

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Code for "FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models (ACL 2024)"

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.

Toolkit for creating, sharing and using natural language prompts.

Locating and editing factual associations in GPT (NeurIPS 2022)

🦜🔗 Build context-aware reasoning applications

[知识编辑] [ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

[知识编辑] Must-read Papers on Knowledge Editing for Large Language Models.

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

A high-throughput and memory-efficient inference and serving engine for LLMs

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…