Havuz

Halo is an open-source framework built by White Circle for training large language and multimodal models

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, ll

Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.

Open Source Instruction Tuning LLM Training Library 2026

Open-source agent execution-recovery controller for coding and tool-using AI agents.

LoRA fine-tune Gemma 4 31B to speak caveman-mode natively. Style: github.com/JuliusBrussee/caveman

Raise your own dragon: fine-tune a language model on your own documents, from R. Writes the training data, trains on your laptop, RAG built

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

Writing that's kin to yours

One GPU. Full LLM workflow. Real benchmarks. No cloud required.

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA,

Serve DeepSeek and Qwen, run an on-demand model library, and fine-tune with Unsloth QLoRA on 2x NVIDIA DGX Spark. TP=2 vLLM lanes behind one