Stars
Algorithmic trading platform: Gauss World Trader using Alpaca Market API
eBPF Observability - Distributed Tracing and Profiling
An AI prompt optimizer for writing better prompts and getting better AI results.
LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost…
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.
Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
Reference PyTorch implementation and models for DINOv3
This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
LLM Finetuning with peft
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。
LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.
1st Place Solution for LLM - Detect AI Generated Text Kaggle Competition
Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.
AI-Powered Python & Python-Powered AI (Python-Use)
A Framework of Small-scale Large Multimodal Models
Natural Language Processing Best Practices & Examples
all kinds of text classification models and more with deep learning
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Curated list of datasets and tools for post-training.