Secunda-0.5-RAW / README.md
Yaroster's picture
Update README.md
f732273 verified
---
license: apache-2.0
language:
- en
tags:
- renpy
- visual-novel
- storytelling
- creative-writing
- llama-3
- qlora
- finetuned
- text-generation
- natural-language-to-script
- instruction-free
inference: false
widget:
- text: "A detective wakes up in a town where no one remembers him."
- text: "Every time she falls asleep, she wakes up in another version of her life."
- text: "A cursed mirror swaps your life with your reflection."
datasets:
- custom
model-index:
- name: Secunda-0.5-RAW
results: []
---
```ascii
β–„β–„β–„β–„β–„ β–„β–ˆβ–ˆβ–ˆβ–„ β–„β–ˆβ–„ β–„ β–„ β–ˆβ–ˆβ–„ β–ˆβ–ˆ β–ˆβ–ˆβ–ˆβ–ˆ β–„β–ˆβ–ˆβ–ˆβ–ˆβ–„
β–ˆ β–€β–„ β–ˆβ–€ β–€ β–ˆβ–€ β–€β–„ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ
β–„ β–€β–€β–€β–€β–„ β–ˆβ–ˆβ–„β–„ β–ˆ β–€ β–ˆ β–ˆ β–ˆβ–ˆ β–ˆ β–ˆ β–ˆ β–ˆβ–„β–„β–ˆ β–ˆ β–ˆ β–ˆβ–„β–„β–„β–„β–„
β–€β–€β–„β–„β–„β–„β–€ β–ˆβ–„ β–„β–€ β–ˆβ–„ β–„β–€ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ β–ˆ
β–€β–ˆβ–ˆβ–ˆβ–€ β–€β–ˆβ–ˆβ–ˆβ–€ β–ˆβ–„ β–„β–ˆ β–ˆ β–ˆ β–ˆ β–ˆβ–ˆβ–ˆβ–€ β–ˆ β–ˆβ–ˆβ–ˆβ–ˆβ–€ β–β–ˆ β–„β–„β–„β–„β–ˆ
β–€β–€β–€ β–ˆ β–ˆβ–ˆ β–ˆ
β–€
β‹†β‹†ΰ­¨ΰ­§Λš THE PRIMΓ‰TOILE ENGINE Λšΰ­¨ΰ­§β‹†ο½‘Λšβ‹†
β€” Visual Novel generation under starlight β€”
```
| Version | Type | Strengths | Weaknesses | Recommended Use |
|-------------------------------------------------------|-----------------|---------------------------------------------------------------------------|----------------------------------------------------------------------|-----------------------------|
| [Secunda-0.1-GGUF](https://huggingface.co/Yaroster/Secunda-0.1-GGUF) / [RAW](https://huggingface.co/Yaroster/Secunda-0.1-RAW) | Instruction | - Most precise<br>- Coherent code<br>- Perfected Modelfile | - Smaller context / limited flexibility | **Production / Baseline** |
| [Secunda-0.3-F16-QA](https://huggingface.co/Yaroster/Secunda-0.3-F16-QA) | QA-based Input | - Acceptable for question-based generation | - Less accurate than 0.1<br>- Not as coherent | Prototyping (QA mode) |
| [Secunda-0.3-F16-TEXT](https://huggingface.co/Yaroster/Secunda-0.3-F16-TEXT) | Text-to-text | - Flexible for freeform tasks | - Slightly off<br>- Modelfile-dependent | Experimental / Text rewrite |
| [Secunda-0.3-GGUF](https://huggingface.co/Yaroster/Secunda-0.3-GGUF) | GGUF build | - Portable GGUF of 0.3 | - Inherits 0.3 weaknesses | Lightweight local testing |
| [Secunda-0.5-RAW](https://huggingface.co/Yaroster/Secunda-0.5-RAW) | QA Natural | - Best QA understanding<br>- Long-form generation potential | - Inconsistent output length<br>- Some instability | Research / Testing LoRA |
| [Secunda-0.5-GGUF](https://huggingface.co/Yaroster/Secunda-0.5-GGUF) | GGUF build | - Portable, inference-ready version of 0.5 | - Shares issues of 0.5 | Offline experimentation |
| [Secunda-0.1-RAW](https://huggingface.co/Yaroster/Secunda-0.1-RAW) | Instruction | - Same base as 0.1-GGUF | - Same as 0.1 | Production backup |
# β‹†βΊβ‚Šβ‹†Secunda ☾ 0.5 RAWβ‹†βΊβ‚Šβ‹†
# <b>For more concise and controlled results, I recommend using [Secunda-0.1-GGUF](https://huggingface.co/Yaroster/Secunda-0.1-GGUF) (instruct) or [Secunda-0.3-GGUF](https://huggingface.co/Yaroster/Secunda-0.3-GGUF) (natural)</b>
**Secunda-0.5-RAW** is the third iteration of the Secunda visual novel generation series, built to transform **natural language story prompts** into fully structured, high-quality Ren'Py scripts β€” without relying on explicit instructions or formatting. It was fine-tuned on a carefully curated dataset of fictional `.rpy` scenes, each paired with its original narrative concept.
This model is much heavier than its siblings: [Secunda-0.1-RAW](https://huggingface.co/Yaroster/Secunda-0.1-RAW), [Secunda-0.3-F16-QA](https://huggingface.co/Yaroster/Secunda-0.3-F16-QA) and [Secunda-0.3-F16-TEXT](https://huggingface.co/Yaroster/Secunda-0.3-F16-TEXT).
<br>Secunda is now based on both direct QA and structured prompting.
---
## πŸš€ Model Highlights
* **Instruction-Free Generation**: Unlike Secunda-0.1, this version relies only on a natural prompt such as *"A detective wakes up in a town where no one remembers him."*
* **Finetuned with QLoRA (FP16)**: Efficient low-resource finetuning using 16-bit precision on LLaMA 3.1 8B.
* **Script-Style Outputs**: Generates structured `.rpy` files, often including characters, backgrounds, dialogue, and a `return`.
* **More Creative Freedom**: Produces more diverse narratives and styles, occasionally multi-scene outputs.
---
<b>/!\ NO HUMAN-MADE DATA WAS USED TO TRAIN THIS AI !
Secunda takes much pride in making sure the training data is scripted ! /!\ </b>
If you like Visual Novels, please visit [itch.io](itch.io) and support independant creators !
## 🧠 Training Details
* **Base model**: `meta-llama/Meta-Llama-3.1-8B`
* **Finetuning**: QLoRA 4-bit adapters (FP16 runtime)
* **Data**: 800+ handcrafted prompt/script pairs in `.jsonl`, each with a raw natural language idea and a full `.rpy` script.
* **Hardware**: NVIDIA RTX 4070
* **Training time**: \~12 hours, 20 epochs
---
## πŸ“ Prompt Style
This model works **without instructions**. Just write your idea naturally:
> "An abandoned cafΓ© reopens every full moon to serve ghosts their last coffee."
---
## ⚠️ Known Issues
* May occasionally produce multiple unrelated scripts in one output if token limit is too high.
* Less deterministic than instruction-based versions β€” retries may help.
* Not always guaranteed to end with `return` (you may add it manually).
---
## πŸ“Œ Tips
* Keep prompts between 10–30 words for best coherence.
* If the output includes multiple scenes, you can split them manually.
* If needed, combine with `sanitize_output()` logic from Secunda-0.1 to postprocess outputs.
---
## πŸ”’ Privacy
This model is private and intended for research and internal tooling for the **PrimΓ©toile** visual novel engine.
---
## πŸ“š License
Apache 2.0 β€” For research, testing, and development only.
---
## ✨ Credits
Trained and maintained by [Yaroster](https://huggingface.co/Yaroster) for the **Secunda** engine inside the PrimΓ©toile framework.