Soup: Fine-tune LLMs from One YAML, Train 8B Model on 4GB GPU
MakazhanAlpamys · github · 2026-08-15
Soup is a Python tool that fine-tunes LLMs from a single YAML config. It uses layer streaming to train an 8B model on a 4GB consumer GPU. Supports LoRA, QLoRA, SFT, DPO, and integrates with GGUF, Ollama. Gained 303 stars today, total 1,431.
More from coding & agent
- Anthropic Tips: Run /compact Before Leaving to Save Tokens — Saboo_Shubham_ · 2026-08-15
- QualCoder MCP: Open-Source Tool for Conversational Qualitative Data Analysis with Claude — nicotem · 2026-08-15
- Anthropic reveals internal benchmark for automated AI research — sachdh · 2026-08-15
- Developer Shares Custom Diagram Skill, Installable with One Command — cneuralnetwork · 2026-08-15
- Agent-Reach: CLI tool gives AI agents free internet access across platforms — PrajwalTomar_ · 2026-08-15
- Microsoft updates Generative AI for Beginners course with RAG guide — bibryam · 2026-08-15