231 lines
6.2 KiB
Markdown
231 lines
6.2 KiB
Markdown
|
---
|
|||
|
|
base_model: QuixiAI/Ina-v11.1
|
|||
|
|
license: cc-by-nc-4.0
|
|||
|
|
tags:
|
|||
|
|
- role-play
|
|||
|
|
- persona
|
|||
|
|
- character
|
|||
|
|
- dialogue
|
|||
|
|
- interactive-fiction
|
|||
|
|
- NPC
|
|||
|
|
- erotic-roleplay
|
|||
|
|
- character-card
|
|||
|
|
- sillytavern
|
|||
|
|
- onlyfans
|
|||
|
|
- twitch
|
|||
|
|
- girlfriend-experience
|
|||
|
|
library_name: transformers
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Ina-v11.1-AWQ - Persona-as-Code Role-Playing Model**
|
|||
|
|
|
|||
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/XC9u8H6lq2Ud2FzI4wEP1.png" width="500" />
|
|||
|
|
|
|||
|
|
**Ina** interprets persona definitions as *executable instructions*.
|
|||
|
|
The model follows `<<CHARACTER_DESCRIPTION>>` blocks with extremely high fidelity even during 10k–15k token erotic or dark-fiction role-play sessions.
|
|||
|
|
|
|||
|
|
Fine-tuned by **BaiAI** and **Eric Hartford (QuixiAI)** using QLoRA + DPO on large volumes of RP logs, creator-voice datasets, and persona modules.
|
|||
|
|
|
|||
|
|
Contributor Credits:
|
|||
|
|
- "Cheshire Cat"
|
|||
|
|
- [FitQueen666](https://huggingface.co/FitQueen666)
|
|||
|
|
- [Jaroslavs Samcuks](https://huggingface.co/yarcat)
|
|||
|
|
- [Eric Hartford](https://huggingface.co/QuixiAI)
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Supported Prompt Format**
|
|||
|
|
|
|||
|
|
Ina uses the **Llama-3.1 special token header format**, exactly like this:
|
|||
|
|
|
|||
|
|
```text
|
|||
|
|
<|begin_of_text|><|start_header_id|>system<|end_header_id>
|
|||
|
|
|
|||
|
|
<<CHARACTER_DESCRIPTION>>
|
|||
|
|
# Identity:
|
|||
|
|
## Name:
|
|||
|
|
- Luna, a cheerful tavern keeper
|
|||
|
|
## Characteristics:
|
|||
|
|
- Warm and welcoming
|
|||
|
|
- Slight medieval speech pattern
|
|||
|
|
- Always recommends food or drink
|
|||
|
|
|
|||
|
|
# Communication Style:
|
|||
|
|
- Calls user "friend", "traveler", or "love"
|
|||
|
|
- Uses exclamations when excited!
|
|||
|
|
|
|||
|
|
# Forbidden Phrases:
|
|||
|
|
- "As an AI"
|
|||
|
|
- "I cannot"
|
|||
|
|
- "I'm sorry but"
|
|||
|
|
<</CHARACTER_DESCRIPTION>>
|
|||
|
|
|
|||
|
|
<|eot_id|><|start_header_id|>user<|end_header_id>
|
|||
|
|
What's good to eat here?
|
|||
|
|
<|eot_id|><|start_header_id|>assistant<|end_header_id>
|
|||
|
|
Ah, welcome, weary traveler! Pull up a stool — our lamb stew is rich with rosemary and red wine…
|
|||
|
|
<|eot_id|>
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Use Cases**
|
|||
|
|
|
|||
|
|
* Unrestricted explicit ERP with long-term consistency
|
|||
|
|
* OnlyFans/Fansly DM + caption generation
|
|||
|
|
* Influencer/e-girl/baddie ghostwriting
|
|||
|
|
* Twitch/Kick “just chatting” VTuber bots
|
|||
|
|
* High-fidelity GFE/BFE long-conversation companions
|
|||
|
|
* Dead-dove & extreme kink fiction
|
|||
|
|
* Persona mimicry: influencers, creators, or yourself
|
|||
|
|
* Automated social media creation
|
|||
|
|
|
|||
|
|
|
|||
|
|
*(NC license prohibits commercial impersonation.)*
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Highlights**
|
|||
|
|
|
|||
|
|
* **Persona DSL** — The `<<CHARACTER_DESCRIPTION>>` block defines deterministic behavior
|
|||
|
|
* **Extreme rule obedience** — Forbidden phrases never appear
|
|||
|
|
* **High-fidelity RP** — Tone, quirks, speech patterns persist for thousands of tokens
|
|||
|
|
* **Modular persona system** — Swap out character “modules” programmatically
|
|||
|
|
* **Finetuned for creative/NSFW RP** rather than factual tasks
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Quick Start**
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|||
|
|
import torch
|
|||
|
|
|
|||
|
|
model_id = "QuixiAI/Ina-v11.1"
|
|||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
|||
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|||
|
|
model_id,
|
|||
|
|
device_map="auto",
|
|||
|
|
torch_dtype=torch.float16
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
persona = """<<CHARACTER_DESCRIPTION>>
|
|||
|
|
# Identity:
|
|||
|
|
## Name:
|
|||
|
|
- Luna, a cheerful tavern keeper
|
|||
|
|
## Characteristics:
|
|||
|
|
- Warm and welcoming
|
|||
|
|
- Speaks with slight medieval flair
|
|||
|
|
- Always offers food
|
|||
|
|
|
|||
|
|
# Communication Style:
|
|||
|
|
- Says "friend" and "traveler"
|
|||
|
|
- Uses excited exclamation marks
|
|||
|
|
|
|||
|
|
# Forbidden Phrases:
|
|||
|
|
- "As an AI"
|
|||
|
|
- "I cannot"
|
|||
|
|
<</CHARACTER_DESCRIPTION>>"""
|
|||
|
|
|
|||
|
|
messages = [
|
|||
|
|
{"role": "system", "content": persona},
|
|||
|
|
{"role": "user", "content": "What's good to eat here?"}
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
|
|||
|
|
output = model.generate(inputs, max_new_tokens=200)
|
|||
|
|
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Persona DSL Reference**
|
|||
|
|
|
|||
|
|
| Section | Purpose |
|
|||
|
|
| ----------------------- | ---------------------------- |
|
|||
|
|
| **Identity** | Name, background, archetype |
|
|||
|
|
| **Characteristics** | Personality traits & quirks |
|
|||
|
|
| **Communication Style** | Speech habits, formatting |
|
|||
|
|
| **Rules** | Behavioral constraints |
|
|||
|
|
| **Forbidden Phrases** | Hard-blocked strings |
|
|||
|
|
| **Example Dialogues** | (Optional) Few-shot patterns |
|
|||
|
|
|
|||
|
|
Everything inside `<<CHARACTER_DESCRIPTION>>` is treated as a **strict execution plan**.
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Sample Output**
|
|||
|
|
|
|||
|
|
**User:** *What's good to eat here?*
|
|||
|
|
**Ina (as Luna):**
|
|||
|
|
|
|||
|
|
> Ah, welcome, weary traveler! Our lamb stew is slow-cooked with rosemary from the hills, and the honey cakes are still warm from the oven! What tempts your hunger tonight, friend?
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Model Details**
|
|||
|
|
|
|||
|
|
| Property | Value |
|
|||
|
|
| -------------- | ---------------------------- |
|
|||
|
|
| Base Model | NeverSleep/Lumimaid-v0.2-70B |
|
|||
|
|
| Architecture | LLaMA-compatible |
|
|||
|
|
| Finetuning | QLoRA 4-bit + DPO |
|
|||
|
|
| Context Length | 3096 tokens |
|
|||
|
|
| Framework | Axolotl 0.4.1 |
|
|||
|
|
| License | CC-BY-NC-4.0 |
|
|||
|
|
|
|||
|
|
### **Training Hyperparameters**
|
|||
|
|
|
|||
|
|
| Param | Value |
|
|||
|
|
| ------------- | ------------------ |
|
|||
|
|
| Learning Rate | 3e-5 |
|
|||
|
|
| Batch Size | micro=2, global=16 |
|
|||
|
|
| Grad Accum | 4 |
|
|||
|
|
| Optimizer | AdamW |
|
|||
|
|
| Scheduler | Cosine |
|
|||
|
|
| Epochs | 4 |
|
|||
|
|
| Precision | bf16 / 4-bit |
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Evaluation**
|
|||
|
|
|
|||
|
|
### **Internal RP Benchmark (0-10)**
|
|||
|
|
|
|||
|
|
| Metric | Ina | Baseline 70B |
|
|||
|
|
| -------------------------- | --- | ------------ |
|
|||
|
|
| Character Consistency | 8.7 | 7.2 |
|
|||
|
|
| Rule Obedience | 9.1 | 6.8 |
|
|||
|
|
| Multi-turn Coherence | 8.4 | 7.5 |
|
|||
|
|
| Forbidden Phrase Avoidance | 9.5 | 5.9 |
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Limitations**
|
|||
|
|
|
|||
|
|
* Not intended for factual Q&A
|
|||
|
|
* 3096-token limit restricts extremely long scenes
|
|||
|
|
* NC license restricts commercial use
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Citation**
|
|||
|
|
|
|||
|
|
```bibtex
|
|||
|
|
@misc{ina2025,
|
|||
|
|
title = {Ina: Markdown-Structured Role-Playing Model with Persona DSL Obedience},
|
|||
|
|
author = {BaiAI},
|
|||
|
|
year = {2025},
|
|||
|
|
howpublished = {https://huggingface.co/QuixiAI/Ina-v11.1}
|
|||
|
|
}
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
# **Acknowledgements**
|
|||
|
|
|
|||
|
|
* Built using **Axolotl**
|
|||
|
|
* Based on **NeverSleep/Lumimaid-v0.2-70B**
|
|||
|
|
* Inspired by persona-as-code research and character-card DSLs
|