gemma4-style-step3000-GGUF

Gemma 4 Style (step 3000) — GGUF

Merged Gemma 4 26B-A4B style-evaluator LoRA at checkpoint step 3000, converted to GGUF for llama.cpp / LM Studio.

This is a prose style judge, not a fiction writer. Full intended use, training details, data sources, and the 14 Style-in-Fiction rubric metrics are documented on the companion LoRA card:

→ alexokita/gemma4-style-lora-step3000

Files

F16 intermediate (~48 GB) was built locally for conversion and is not uploaded here.

Intended use (short)

• Emit JSON style_profiles and short judgments over the 14 SiF-derived metrics
• Score drafts against steering cards (voice / style / tone)
• Power evaluator bake-offs and later writer ↔ evaluator loops

Not for: open-ended novel writing.

Recommended sampling (LM Studio / llama.cpp)

From the Gemma 4 QAT model card: temperature 1.0, top_p 0.95, top_k 64, thinking off for JSON / classification.

How it was trained (summary)

The 14 Style-in-Fiction metrics

Operationalized from Leech & Short, Style in Fiction (2nd ed.) in style_rubric.json:

1. lexical_complexity — LLM Pass 1
2. lexical_density — computable (spaCy)
3. register — LLM Pass 1
4. sentence_complexity — LLM Pass 1
5. sentence_length_mean — computable
6. subordination_ratio — computable
7. figurative_density — LLM Pass 1
8. cohesion — LLM Pass 1
9. dialogue_ratio — computable
10. pov — LLM Pass 1
11. mind_style — LLM Pass 2
12. narrative_distance — LLM Pass 2
13. free_indirect_discourse — LLM Pass 2
14. tone — LLM Pass 2

Labels: Phase 1 distilled the rubric from the book; Phase 2 classified prose with computables + multi-pass LLM + RAG; Phase 3 built SFT pairs. See the LoRA card for the full table and value enums.

License

Use of the base Gemma 4 weights is subject to the Gemma license.