mofanv

HowToLiveLonger

程序员延寿指南 | A programmer's guide to live longer

alphafold

Open source code for AlphaFold.

flash-attention

Fast and memory-efficient exact attention

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

MemGPT

Building persistent LLM agents with long-term memory 📚🦙

pikvm

Open and inexpensive DIY IP-KVM based on Raspberry Pi

axolotl

Go ahead and axolotl questions

promptbase

All things prompt engineering

instructor

structured outputs for llms

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

lean4

Lean 4 programming language and theorem prover

i2pd

🛡 I2P: End-to-End encrypted and anonymous Internet

Eureka

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models"

Video-LLaVA

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

catala

Programming language for literate programming law specification

diplomacy_cicero

Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

awesome-knowledge-graph

A curated list of Knowledge Graph related learning materials, databases, tools and other resources

CRATE

Code for CRATE (Coding RAte reduction TransformEr).

LookaheadDecoding

factool

FacTool: Factuality Detection in Generative AI

CKG

Clinical Knowledge Graph (CKG) is a platform with twofold objective: 1) build a graph database with experimental data and data imported from diverse biomedical databases 2) automate knowledge discovery making use of all the information contained in the graph

tiger

Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

clownfish

Constrained Decoding for LLMs against JSON Schema

q-transformer

Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind

GPTFuzz

Official repo for GPTFUZZER : Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

jade-db

"他山之石、可以攻玉"：复旦白泽智能发布面向国内开源和国外商用大模型的Demo数据集JADE-DB

HallusionBench

[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

vllm-safety-benchmark

Official PyTorch Implementation of "How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs"