|
|
--- |
|
|
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: |
|
|
- meta-llama/Llama-3.2-1B |
|
|
pipeline_tag: text-generation |
|
|
library_name: peft |
|
|
metrics: |
|
|
- character |
|
|
--- |
|
|
# WARNING: THIS MODEL IS NOW DEPRICATED, Please Use MiniMaid-L2 for An Even Better 1B model! |
|
|
<a href="https://ibb.co/GvDjFcVp"><img src="https://raw.githubusercontent.com/Nexus-Network-Interactives/HuggingfacePage/refs/heads/main/MiniMaid-L1.png" alt="image" border="0"></a> |
|
|
|
|
|
# MiniMaid-L1 |
|
|
- Introducing Our Brand New Open-sourced AI model named MiniMaid-L1, Minimaid Boast a staggering **1B params** with |
|
|
Good Coherent Story telling, Capable roleplaying ability **(Due to its 1B params, it might produce bad and repetitive output)**. |
|
|
|
|
|
- **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-L1 is 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 **C**, |
|
|
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-L1 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:** Mosher-R1(Propietary Software) |
|
|
|
|
|
- MiniMaid-L1 Official Metric Score |
|
|
 |
|
|
- Metrics Made By **ItsMeDevRoland** |
|
|
Which compares: |
|
|
- **Deepseek R1 3B GGUF** |
|
|
- **Dolphin 3B GGUF** |
|
|
- **Hermes 3b Llama GGUFF** |
|
|
- **MiniMaid-L1 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-L1: A 1B Roleplay Assistant That Punches Above Its Weight |
|
|
|
|
|
> She’s not perfect — but she’s fast, compact, and learning quick. And most importantly, **she didn’t suck**. |
|
|
|
|
|
Despite her size, MiniMaid-L1 held her own against 3B models like **DeepSeek**, **Dolphin**, and **Hermes**. |
|
|
 |
|
|
💬 **Roleplay Evaluation (v0)** |
|
|
- 🧠 Character Consistency: 0.50 |
|
|
- 🌊 Immersion: 0.13 |
|
|
- 🧮 Overall RP Score: 0.51 |
|
|
- ✏️ Length Score: 0.91 |
|
|
|
|
|
- Even with only 1.5K synthetic samples, MiniMaid showed strong prompt structure, consistency, and resilience. |
|
|
--- |
|
|
 |
|
|
📊 **Efficiency Wins** |
|
|
- **Inference Time:** 49.1s (vs Hermes: 140.6s) |
|
|
- **Tokens/sec:** 7.15 (vs Dolphin: 3.88) |
|
|
- **BLEU/ROUGE-L:** Outperformed DeepSeek + Hermes |
|
|
|
|
|
- MiniMaid proved that **you don’t need 3 billion parameters to be useful** — just smart distillation and a little love. |
|
|
--- |
|
|
🛠️ **MiniMaid is Built For** |
|
|
- Lightweight RP generation |
|
|
- Low-resource hardware |
|
|
- High customization potential |
|
|
|
|
|
🌱 **She’s just getting started** — v1 is on the way with more character conditioning, dialogue tuning, and narrative personality control. |
|
|
|
|
|
--- |
|
|
> “She’s scrappy, she’s stubborn, and she’s still learning. But MiniMaid-L1 proves that smart distillation and a tiny budget can go a long way — and she’s only going to get better from here.” |
|
|
--- |
|
|
|
|
|
- # 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 |
|
|
|
