Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

A pytorch quantization backend for optimum

The Triton TensorRT-LLM Backend

DLRover: An Automatic Distributed Deep Learning System

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Apache HertzBeat(incubating) is a real-time monitoring system with agentless, performance cluster, prometheus-compatible, custom monitoring and status page building capabilities.

Fine-tune LLM agents with online reinforcement learning

塔罗、扑克牌卡片的洗牌、选牌、翻转等动画

get a tarrot reading from AI

Reference implementation for DPO (Direct Preference Optimization)

Making large AI models cheaper, faster and more accessible

Generative Representational Instruction Tuning

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

leaked prompts of GPTs

A generalized information-seeking agent system with Large Language Models (LLMs).

[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct

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

A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models

Rectified Rotary Position Embeddings

Kanu is an algebra calculator built in Python. There are no non-stdlib dependencies.

Official inference library for Mistral models

Official implementation of paper "Cumulative Reasoning With Large Language Models" (https://arxiv.org/abs/2308.04371)

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Ongoing research training transformer models at scale

A guidance language for controlling large language models.

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Generate comic panels using a LLM + SDXL. Powered by Hugging Face 🤗