R_REDDYX.XYZ
AIPython★ 9,433⑂ 798 forksApache-2.0

oumi-ai/oumi

OUMI EASY LLM TUNING

OUMI lets you quickly fine‑tune (SFT/RL), evaluate, and deploy Qwen, Gemma, and any open agentic LLM/VLM without extra complexity.

// KEY FEATURES

  • Fine‑tune models using SFT or RL with a single command.
  • Automatically assess quality on benchmarks like MMLU, GSM8K, and more.
  • Export the model to Hugging Face and run it via vLLM or Triton.
  • Supports Qwen, Gemma, and any open agentic LLM/VLM through a unified API.
#agentic-ai#dpo#fine-tuning#gemma#gpt-oss#grpo#inference#llama#llm#llm-as-a-judge#llm-evaluation#llms
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

Free GPT without Plus★ 9432ATLAS: GIT FOR AI AGENTS★ 9426AI Agent Learning Framework★ 9414MobileAgent Powerful GUI Agent★ 9379ORKAS: Multi-agent AI Assistant★ 9374Claude-Powered App Cloner★ 9361

← FULL CATALOG

oumi-ai/oumi — Oumi Easy LLM Tuning | REDDYX AI