Doohae

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Language:Jupyter NotebookNOASSERTION10917 88 300

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

Language:Jupyter NotebookMIT9756 84 247

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.

Language:Shell3434 29 422

sglang

SGLang is yet another fast serving framework for large language models and vision language models.

Language:PythonApache-2.03414 36 309

Qwen-Agent

Agent framework and applications built upon Qwen2, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.

Language:PythonNOASSERTION2776 28 267

scancode-toolkit

:mag: ScanCode detects licenses, copyrights, dependencies by "scanning code" ... to discover and inventory open source and third-party packages used in your code. Sponsored by NLnet project https://nlnet.nl/project/vulnerabilitydatabase, the Google Summer of Code, Azure credits, nexB and others generous sponsors!

Language:Python2036 73 2531

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

Language:PythonApache-2.01911 19 77

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

Language:PythonApache-2.01826 16 149

starcoder2

Home of StarCoder2!

Language:PythonApache-2.01637 17 17

SWE-bench

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

Language:PythonMIT1536 22 115

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Language:PythonApache-2.01287 17 48

distilabel

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

Language:PythonApache-2.01204 14 355

evolutionary-model-merge

Official repository of Evolutionary Optimization of Model Merging Recipes

Language:PythonApache-2.01122 40 11

lightning-thunder

Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

Language:PythonApache-2.01093 33 348