|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- unsloth |
|
|
- Uncensored |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- llama |
|
|
- trl |
|
|
- roleplay |
|
|
- conversational |
|
|
datasets: |
|
|
- iamketan25/roleplay-instructions-dataset |
|
|
- N-Bot-Int/Iris-Uncensored-R1 |
|
|
- N-Bot-Int/Moshpit-Combined-R2-Uncensored |
|
|
- N-Bot-Int/Mushed-Dataset-Uncensored |
|
|
- N-Bot-Int/Muncher-R1-Uncensored |
|
|
- N-Bot-Int/Millia-R1_DPO |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- N-Bot-Int/MiniMaid-L1 |
|
|
pipeline_tag: text-generation |
|
|
library_name: peft |
|
|
metrics: |
|
|
- character |
|
|
- bleu |
|
|
- rouge |
|
|
--- |
|
|
# THIS IS THE FINAL MiniMaid-L Series, This is because we've hit the final Ceiling for a 1B model! Thank you so much for your Support! |
|
|
- If you loved our Models, then please consider donating and supporting us through Ko-fi! |
|
|
- [](https://ko-fi.com/J3J61D8NHV) |
|
|
|
|
|
 |
|
|
# MiniMaid-L3 |
|
|
- Introducing MiniMaid-L3 model! Our brand new finetuned MiniMaid-L2 Architecture, allowing for an Even More Coherent and |
|
|
Immersive Roleplay through the Use of Knowledge distillation! |
|
|
|
|
|
- MiniMaid-L3 is a Small Update to L2, Which uses Knowledge distillation to combine our L2 Architecture, and A Popular |
|
|
Roleplaying Model named MythoMax, which also uses a Combanant Technology to Combine models and create MythoMax-7B, |
|
|
MiniMaid-L3 on the other hand is a distillation of MiniMaid-L2, combined with using MythoMax Knowledge Distillation, |
|
|
which created MiniMaid-L3, a More Capable Model that Outcompete its descendance in both roleplaying scenarios |
|
|
And even Knock MiniMaid-L2's BLEU scoring! |
|
|
|
|
|
|
|
|
# MiniMaid-L1 Base-Model Card Procedure: |
|
|
- **MiniMaid-L1** achieve a good Performance through process of DPO and Combined Heavy Finetuning, To Prevent Overfitting, |
|
|
We used high LR decays, And Introduced Randomization techniques to prevent the AI from learning and memorizing, |
|
|
However since training this on Google Colab is difficult, the Model might underperform or underfit on specific tasks |
|
|
Or overfit on knowledge it manage to latched on! However please be guided that we did our best, and it will improve as we move onwards! |
|
|
|
|
|
- MiniMaid-L3 is Another Instance of Our Smallest Model Yet! if you find any issue, then please don't hesitate to email us at: |
|
|
[[email protected]](mailto:[email protected]) |
|
|
about any overfitting, or improvements for the future Model **V4**, |
|
|
Once again feel free to Modify the LORA to your likings, However please consider Adding this Page |
|
|
for credits and if you'll increase its **Dataset**, then please handle it with care and ethical considerations |
|
|
|
|
|
|
|
|
|
|
|
- MiniMaid-L3 is |
|
|
- **Developed by:** N-Bot-Int |
|
|
- **License:** apache-2.0 |
|
|
- **Parent Model from model:** unsloth/llama-3.2-3b-instruct-unsloth-bnb-1bit |
|
|
- **Dataset Combined Using:** NKDProtoc(Propietary Software) |
|
|
|
|
|
- MiniMaid-L3 Official Metric Score |
|
|
 |
|
|
- Metrics Made By **ItsMeDevRoland** |
|
|
Which compares: |
|
|
- **MiniMaid-L2 GGUFF** |
|
|
- **MiniMaid-L3 GGUFF** |
|
|
Which are All Ranked with the Same Prompt, Same Temperature, Same Hardware(Google Colab), |
|
|
To Properly Showcase the differences and strength of the Models |
|
|
|
|
|
- **Visit Below to See details!** |
|
|
|
|
|
--- |
|
|
# 🧵 MiniMaid-L3: Slower Steps, Deeper Stories — The Immersive Upgrade |
|
|
> "She’s more grounded, more convincing — and when it comes to roleplay, she’s in a league of her own." |
|
|
 |
|
|
--- |
|
|
|
|
|
# MiniMaid-L3 doesn’t just iterate — she elevates. Built on L2’s disciplined architecture, L3 doubles down on character immersion and emotional coherence, refining every line she delivers. |
|
|
- 💬 Roleplay Evaluation (v2) |
|
|
- 🧠 Character Consistency: 0.54 → 0.55 (+) |
|
|
- 🌊 Immersion: 0.59 → 0.66 (↑) |
|
|
- 🎭 Overall RP Score: 0.72 → 0.75 |
|
|
> L3’s immersive depth marks a new high in believability and emotional traction — she's not just playing a part, she becomes it. |
|
|
|
|
|
# 📊 Slower, But Smarter |
|
|
- 🕒 Inference Time: 39.1s (↑ from 34.5s) |
|
|
- ⚡ Tokens/sec: 6.61 (slight dip) |
|
|
- 📏 BLEU/ROUGE-L: Mixed — slight BLEU gain, ROUGE-L softened |
|
|
> Sure, she takes her time — but it’s worth it. L3 trades a few milliseconds for measured, thoughtful outputs that stick the landing every time. |
|
|
|
|
|
# 🎯 Refined Roleplay, Recalibrated Goals |
|
|
- MiniMaid-L3 isn’t trying to be the fastest. She’s here to be real — holding character, deepening immersion, and generating stories that linger. |
|
|
- 🛠️ Designed For: |
|
|
- Narrative-focused deployments |
|
|
- Long-form interaction and memory retention |
|
|
- Low-size, high-fidelity simulation |
|
|
--- |
|
|
> “MiniMaid-L3 sacrifices a bit of speed to speak with soul. She’s no longer just reacting — she’s inhabiting. It’s not about talking faster — it’s about meaning more.” |
|
|
# MiniMaid-L3 is the slow burn that brings the fire. |
|
|
--- |
|
|
|
|
|
- # Notice |
|
|
- **For a Good Experience, Please use** |
|
|
- Low temperature 1.5, min_p = 0.1 and max_new_tokens = 128 |
|
|
|
|
|
|
|
|
- # Detail card: |
|
|
- Parameter |
|
|
- 1 Billion Parameters |
|
|
- (Please visit your GPU Vendor if you can Run 1B models) |
|
|
|
|
|
- Finetuning tool: |
|
|
- Unsloth AI |
|
|
- This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
|
|
- Fine-tuned Using: |
|
|
- Google Colab |
