Guides
Short, practical guides on fine-tuning open language models. Every number about finetuna's own results comes from a published report you can open.
How to fine-tune a small language model: data, epochs, results
A practical walk-through: scope a narrow task, write the JSONL, pick epochs, read the validation loss and the held-out answers, and know when not to fine-tune. With three real runs.
LoRA vs QLoRA fine-tuning: what changes in practice
What LoRA and QLoRA actually do, when each makes sense, the exact recipe finetuna runs (rank 16, alpha 32, learning rate 2e-4), and what happens between the adapter and the GGUF.
Fine-tune a model and run the GGUF in Ollama
From adapter to a GGUF you can run: what the files are, q4_k_m vs q8_0, a real Modelfile line by line, ollama create and run, and what to check when the answers look wrong.
Fine-tuning vs RAG: a 10-minute check before you spend anything
Fine-tuning changes how a model answers; RAG changes what it can look up. A short checklist to decide, with real runs where fine-tuning helped a lot, a little, and where it could not add knowledge.
Fine-tuning Bielika na własnych danych: ile to kosztuje i co dostajesz (po polsku)
Jak dostroić Bielika 11B na własnym JSONL: format danych, koszt pakietu, dwa prawdziwe przebiegi (wydźwięk recenzji i pytania egzaminacyjne), dane osobowe i granice metody.