---

language:

• en license: gemma license_link: https://ai.google.dev/gemma/docs/gemma_4_license library_name: transformers pipeline_tag: text-generation base_model:
• coder3101/gemma-4-31B-it-heretic base_model_relation: finetune tags:
• roleplay
• creative-writing
• gemma
• gemma4
• qlora
• uncensored
• nsfw
• not-for-all-audiences

---

Lilith-31B-v1.0

Versatile uncensored roleplay / creative-writing model on Gemma-4-31B. Drives any character card (SillyTavern / pluma), built to be lively and varied rather than flat or repetitive. darthcrawl. Explicit-capable.

• Base: coder3101/gemma-4-31B-it-heretic (decensored Gemma-4-31B-it)
• Method: QLoRA r32/alpha64 all-linear, loss masked to model turns, 1 epoch eval-driven. Release = the ~0.39-epoch checkpoint (eval 2.11 vs base 7.03), picked over the fully-trained one to keep prose lively (loss != liveliness).
• Data: ~30M tokens, 8 curated sources (human forum RP, AO3, curated public RP, curated synth), ~40/60 NSFW/SFW.
• Chat template: Gemma-4 (<|turn>user ... <turn|> / <|turn>model ...).
• Sampling tip: DRY + XTC + modest repetition penalty for max variety.

Siblings: Lilith-31B-v1.0 (bf16) | -LoRA | -GGUF | -MLX-4bit/6bit/8bit

Merged bf16 weights (~63 GB). For quantized inference use -GGUF or -MLX-*.