unslothai / unsloth
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
☆15,611Updated this week
Related projects: ⓘ
- A high-throughput and memory-efficient inference and serving engine for LLMs☆26,822Updated this week
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆9,780Updated this week
- A modular graph-based Retrieval-Augmented Generation (RAG) system☆17,179Updated this week
- Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datase…☆11,582Updated last week
- Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)☆30,812Updated this week
- DSPy: The framework for programming—not prompting—foundation models☆16,773Updated this week
- RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.☆17,176Updated this week
- Python SDK, Proxy Server to call 100+ LLM APIs using the OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker,…☆12,231Updated this week
- Go ahead and axolotl questions☆7,554Updated this week
- Create LLM agents with long-term memory and custom tools 📚🦙☆11,378Updated this week
- Official inference library for Mistral models☆9,514Updated this week
- The Memory layer for your AI apps☆21,765Updated this week
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆19,294Updated last month
- Large Language Model Text Generation Inference☆8,762Updated this week
- LLM based autonomous agent that does online comprehensive research on any given topic☆14,029Updated this week
- Run any open-source LLMs, such as Llama 3.1, Gemma, as OpenAI compatible API endpoint in the cloud.☆9,731Updated last week
- llama3 implementation one matrix multiplication at a time☆13,085Updated 3 months ago
- Universal LLM Deployment Engine with ML Compilation☆18,642Updated this week
- Convert PDF to markdown quickly with high accuracy☆16,438Updated last week
- the AI-native open-source embedding database☆14,555Updated this week
- Build AI Assistants with memory, knowledge and tools.☆11,145Updated this week
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆7,620Updated 4 months ago
- QLoRA: Efficient Finetuning of Quantized LLMs☆9,906Updated 3 months ago
- LlamaIndex is a data framework for your LLM applications☆35,450Updated this week
- High-speed Large Language Model Serving on PCs with Consumer-grade GPUs☆7,877Updated last week
- SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-…☆13,302Updated this week
- An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.☆10,156Updated last week
- A programming framework for agentic AI 🤖☆30,821Updated this week
- 🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.☆13,879Updated this week
- Python bindings for llama.cpp☆7,723Updated this week