R_REDDYX.XYZ
AIPython★ 10,552⑂ 1,747 forksApache-2.0

MakazhanAlpamys/Soup

Soup: Train LLM Easily

Soup fine-tunes an LLM from a single YAML using a streaming layer — enabling an 8B model to run on a laptop with 4 GB VRAM.

// KEY FEATURES

  • Training an 8B model on a 4 GB GPU
  • One YAML file for the entire configuration
  • Streaming layer reduces memory consumption
#cli#consumer-gpu#dpo#fine-tuning#gguf#huggingface#llm#llmops#local-ai#local-llm#lora#low-vram
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

Voice AI Agents Framework★ 10540Safe sandbox for AI★ 10600AI Expert Collection★ 10617Blinko: Personal notes with AI★ 10470DSH Web GUI Plugin Ecosystem★ 10428OPEN SOURCE AI FOR LANGUAGES★ 10426

← FULL CATALOG

MakazhanAlpamys/Soup — Soup: Train LLM Easily | REDDYX AI