Foundation Model Evaluations Library

An automated pipeline for evaluating LLMs for role-playing.

Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

Benchmark for LLM Reasoning & Understanding with Challenging Tasks from Real Users.

使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

A Collection of Variational Autoencoders (VAE) in PyTorch.

#1 Locally hosted web application that allows you to perform various operations on PDF files

The memory layer for Personalized AI

这是一个基于StyleGAN的人脸属性编辑器

LlamaIndex is a data framework for your LLM applications

Prefix-Tuning: Optimizing Continuous Prompts for Generation

code for the ICLR'22 paper: On Robust Prefix-Tuning for Text Classification

Brand new TTS solution

Bring portraits to life!

一本 GPT4 生成的单词书📚，超过 8000 个单词分析，涵盖了词义、例句、词根词缀、变形、文化背景、记忆技巧和小故事

Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

Robust recipes to align language models with human and AI preferences

使用Bert完成实体之间关系抽取

Example Python code for comparing documents using MinHash

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Using GPT to parse PDF

大模型多维度中文对齐评测基准 (ACL 2024)

High-quality datasets, tools, and concepts for LLM fine-tuning.

Odysseus: Playground of LLM Sequence Parallelism