sudokuLLM

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! ?

Find secrets with Gitleaks ?

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2.5, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL2, Phi3.5-Vision, GOT-OCR2, ...).

Efficient Triton Kernels for LLM Training

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Code examples and resources for DBRX, a large language model developed by Databricks

dstack is a lightweight, open-source alternative to Kubernetes & Slurm, simplifying AI container orchestration with multi-cloud & on-prem support. It natively supports NVIDIA, AMD, TPU, and Intel accelerators.

MoBA: Mixture of Block Attention for Long-Context LLMs