unslothai / unslothLinks
Fine-tuning & Reinforcement Learning for LLMs. π¦₯ Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
β48,786Updated last week
Alternatives and similar repositories for unsloth
Users that are interested in unsloth are comparing it to the libraries listed below
Sorting:
- A high-throughput and memory-efficient inference and serving engine for LLMsβ64,235Updated this week
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)β63,378Updated this week
- Go ahead and axolotl questionsβ10,870Updated this week
- Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.β156,856Updated this week
- SGLang is a fast serving framework for large language models and vision language models.β20,874Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.β13,000Updated this week
- Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing aβ¦β31,849Updated this week
- LLM inference in C/C++β90,838Updated this week
- User-friendly AI Interface (Supports Ollama, OpenAI API, ...)β117,009Updated this week
- Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We alsβ¦β18,061Updated last month
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.β12,558Updated 2 months ago
- A modular graph-based Retrieval-Augmented Generation (RAG) systemβ29,543Updated this week
- Python bindings for llama.cppβ9,786Updated 3 months ago
- The official Meta Llama 3 GitHub siteβ29,116Updated 10 months ago
- RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to creatβ¦β68,703Updated this week
- Inference code for Llama modelsβ58,968Updated 10 months ago
- Train transformer language models with reinforcement learning.β16,473Updated last week
- An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.β39,287Updated 6 months ago
- LlamaIndex is the leading framework for building LLM-powered agents over your data.β45,533Updated last week
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.β24,064Updated last year
- Fully open reproduction of DeepSeek-R1β25,701Updated last week
- π€ PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.β20,157Updated 2 weeks ago
- π¦π The platform for reliable agents.β121,085Updated this week
- Universal memory layer for AI Agentsβ43,677Updated last week
- A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizationsβ16,129Updated this week
- A programming framework for agentic AIβ52,125Updated last month
- Ollama Python libraryβ8,932Updated 2 weeks ago
- aider is AI pair programming in your terminalβ38,763Updated last week
- ππ€ Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyNβ56,514Updated last week
- Build resilient language agents as graphs.β21,539Updated last week