|
|
--- |
|
|
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-0.3-F16-QA |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
|
|
|
```ascii |
|
|
|
|
|
βββββ βββββ βββ β β βββ ββ βββββ ββ |
|
|
β ββ ββ β ββ ββ β β β β β β β β ββ |
|
|
β βββββ ββββ β β β β ββ β β β ββββ β β ββ |
|
|
βββββββ ββ ββ ββ ββ β β β β β β β β β β β ββ |
|
|
βββββ βββββ ββ ββ β β β ββββ β βββββ ββ β |
|
|
βββ β ββ β |
|
|
β |
|
|
|
|
|
ββΰ¨ΰ§Λ THE PRIMΓTOILE ENGINE Λΰ¨ΰ§βｑΛβ |
|
|
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 | |
|
|
|
|
|
--- |
|
|
|
|
|
## π Overview |
|
|
|
|
|
**Secunda-0.1-RAW** is the original release of the Secunda fine-tuned model family, trained to produce polished **Ren'Py `.rpy` scripts** from structured instructions! |
|
|
|
|
|
The model outputs: |
|
|
|
|
|
* `define` blocks for named characters (with colors!) |
|
|
* `image` declarations for scenes & sprites |
|
|
* A clear `label start:` structure |
|
|
* Emotional dialogue, branching `menu`s, `jump`s, and proper `return` |
|
|
|
|
|
This version is *the most stable so far* β often more reliable than 0.3! |
|
|
|
|
|
--- |
|
|
|
|
|
<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 ! |
|
|
|
|
|
|
|
|
## β¨ Moonlight Specs |
|
|
|
|
|
* **Base model**: `meta-llama/Meta-Llama-3.1-8B` |
|
|
* **Fine-tuning**: QLoRA (r=64, alpha=16, dropout=0.1) |
|
|
* **Precision**: Float16 (FP16) |
|
|
* **Max tokens**: 4096 |
|
|
* **Hardware used**: RTX 4070, 64GB RAM |
|
|
|
|
|
--- |
|
|
|
|
|
## πͺ Inference in the Starlight |
|
|
|
|
|
### Setup |
|
|
|
|
|
## π Quick Start |
|
|
|
|
|
### Installation |
|
|
|
|
|
```bash |
|
|
pip install transformers accelerate peft bitsandbytes |
|
|
``` |
|
|
|
|
|
### Inference Script Example |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
from peft import PeftModel |
|
|
import torch |
|
|
|
|
|
BASE_MODEL = "meta-llama/Meta-Llama-3.1-8B" |
|
|
LORA_PATH = "path/to/Secunda-0.1-RAW" |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(BASE_MODEL, torch_dtype=torch.float16, device_map="auto") |
|
|
model = PeftModel.from_pretrained(model, LORA_PATH) |
|
|
tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL) |
|
|
|
|
|
def build_prompt(idea): |
|
|
return f"""You are an expert writer of visual novels in Ren'Py. |
|
|
Generate a complete and polished Ren'Py script based on the following concept: |
|
|
|
|
|
\"\"\"{idea}\"\"\" |
|
|
|
|
|
Your output should include: |
|
|
- `define` blocks for all characters (with names and color codes) |
|
|
- `image` blocks for key backgrounds and character sprites |
|
|
- `label start:` with a clear beginning |
|
|
- Proper `scene`, `show`, `menu`, `play music/sound`, and `jump` statements |
|
|
- Emotional dialogue and natural pacing |
|
|
- A proper ending (`return`) or narrative closure |
|
|
|
|
|
Structure the script as a `.rpy` file β do not include explanations, comments, or placeholder text.""" |
|
|
|
|
|
prompt = build_prompt("A young girl finds a photo album that shows moments that haven't happened yet.") |
|
|
inputs = tokenizer(prompt, return_tensors="pt").to(model.device) |
|
|
|
|
|
with torch.no_grad(): |
|
|
outputs = model.generate(**inputs, max_new_tokens=2048, temperature=0.85, top_p=0.95) |
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
|
``` |
|
|
|
|
|
|
|
|
--- |
|
|
|
|
|
## π Evaluation |
|
|
|
|
|
This model has: |
|
|
|
|
|
* Generated 1000+ `.rpy` files |
|
|
* Passed human review for structure, creativity & syntax |
|
|
* > 90% valid output with minimal manual tweaks |
|
|
|
|
|
--- |
|
|
|
|
|
## βοΈ Talking to the Moon |
|
|
|
|
|
If you use **Secunda-0.1-RAW**, please star and cite: |
|
|
|
|
|
```bibtex |
|
|
@misc{secunda2025, |
|
|
title={Secunda-0.1-RAW}, |
|
|
author={Yaroster}, |
|
|
year={2025}, |
|
|
note={https://huggingface.co/Yaroster/Secunda-0.1-RAW} |
|
|
} |
|
|
``` |
|
|
|
|
|
--- |
|
|
|
|
|
## πͺ From the Cosmos |
|
|
|
|
|
* [Secunda-0.3-F16-QA](https://huggingface.co/Yaroster/Secunda-0.3-F16-QA) β experimental question-answer variant |
|
|
* [Secunda-0.3-F16-TEXT](https://huggingface.co/Yaroster/Secunda-0.3-F16-TEXT) β for less structured generation |
|
|
* [PrimΓ©toile](https://yaroster.com) β full VN pipeline |
|
|
|
|
|
--- |
|
|
|
|
|
βΒ°.βΎ Secunda-0.1-RAW β½.Β°β |
|
|
|
|
|
> β§ Because every visual novel deserves to begin with a spark of magic β§ |
|
|
|
|
|
β οΈ This repo contains **only the LoRA adapter weights**. To use the model, download the base `LLaMA 3.1` from Meta (terms apply): [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) |
|
|
|
