[NeurIPS 2024] Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method

[NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages

An automated pipeline for evaluating LLMs for role-playing.

✨✨A curated list of latest advances on Large Foundation Models with Federated Learning

Instruction/chat prompts creation library for text generation LLMs. It supports local and Hugging Face models.

Jinja2 chat templates for popular LLM models

Collection of Basic Prompt Templates for Various Chat LLMs (Chat LLM 的基础提示模板集合)

Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

RDP Wrapper Library

RDP Wrapper Library

Code and documentation to train Stanford's Alpaca models, and generate the data.

Witness the aha moment of VLM with less than $3.

The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & k…

AI模型接口管理与分发系统，支持将多种大模型转为OpenAI格式调用、支持Midjourney Proxy、Suno、Rerank，兼容易支付协议，可供个人或者企业内部管理与分发渠道使用，本项目基于One API二次开发。🍥 The next-generation LLM gateway and AI asset management system supports multiple lan…

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Experiments with local as well as models available through an api

Prompt tuning for GPT-J

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

nonebot plugin that can help manage addons folder in Left 4 Dead 2 server nonebot插件，用来在Q群中管理求生之路服务器上的addons文件夹

Summarize existing representative LLMs text datasets.

Reference implementation for DPO (Direct Preference Optimization)

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).