Stars
- All languages
- ApacheConf
- Arduino
- Assembly
- Batchfile
- C
- C#
- C++
- CMake
- CSS
- Classic ASP
- Clojure
- CoffeeScript
- Common Workflow Language
- Cython
- Dockerfile
- Erlang
- Go
- HTML
- Java
- JavaScript
- Jsonnet
- Julia
- Jupyter Notebook
- KiCad Layout
- Kotlin
- Lua
- MATLAB
- Makefile
- Objective-C
- Objective-C++
- OpenEdge ABL
- PDDL
- PHP
- Perl
- PowerShell
- PureBasic
- Python
- R
- Roff
- Ruby
- Rust
- SAS
- Scala
- Shell
- Smarty
- Swift
- SystemVerilog
- Tcl
- TeX
- TypeScript
- Vim Script
- Vue
Pretraining code for a large-scale depth-recurrent language model
A time-series database for high-performance real-time analytics packaged as a Postgres extension
🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.
The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.
An object-oriented algebraic modeling language in Python for structured optimization problems.
"MiniRAG: Making RAG Simpler with Small and Free Language Models"
🌐 WebWalker: Benchmarking LLMs in Web Traversal
Jupyter notebook tutorials from QuantConnect website for Python, Finance and LEAN.
PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant refe…
Fully open reproduction of DeepSeek-R1
This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data
verl: Volcano Engine Reinforcement Learning for LLMs
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai
百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,集成DeepSeek R1等优秀大模型,时延低至800ms,低配置也可运行,支持打断
The ultimate LLM application development framework in Golang.
An extremely fast Python package and project manager, written in Rust.
Free trading strategies for Freqtrade bot
Sky-T1: Train your own O1 preview model within $450
AirLLM 70B inference with single 4GB GPU
TradeMaster is an open-source platform for quantitative trading empowered by reinforcement learning 🔥 ⚡ 🌈
Automatically split your PyTorch models on multiple GPUs for training & inference
PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism