LenslessFace : An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification

[NeurIPS'24] Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models

Arena-Hard-Auto: An automatic LLM benchmark.

A Native-PyTorch Library for LLM Fine-tuning

[ACL'24] Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization

[ACL'24, Outstanding Paper] Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!

[ACL 2024 Findings] The official repo for "ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models".

[ACL 2024] MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues

[CVPR'24] Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors

A framework for few-shot evaluation of autoregressive language models.

Code for the paper LEGO-Prover: Neural Theorem Proving with Growing Libraries

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.

Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" (ICLR 2024)

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

Aligning LMMs with Factually Augmented RLHF

Assignment Solutions for Berkeley CS 285: Deep Reinforcement Learning (Fall 2021)

Reference implementation for DPO (Direct Preference Optimization)

Some Conferences' accepted paper lists (including AI, ML, Robotic)

An Implementation of "Orca: Progressive Learning from Complex Explanation Traces of GPT-4"

[CVPR 2023] ReasonNet: End-to-End Driving with Temporal and Global Reasoning

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

Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

RSS 2023: This repository contains code for the paper Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors.

基于ChatGLM-6B + LoRA的Fintune方案

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.