Downloads · 30 days
741
23% of all-time downloads
limloop/MN-12B-LucidFaun-RP-RU-GGUF
MN-12B-LucidFaun-RP-RU-GGUF is a machine learning model from limloop. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Downloads · 30 days
741
23% of all-time downloads
All-time downloads
3.2K
Public
Repo size
37.4 GB
Likes
2
Public
Click a slice to open those files.
.gguf37.4 GB · 100%
From the Hugging Face model README
MN-12B-LucidFaun-RP-RU — гибридная модель на базе Mistral Nemo 12B, созданная методом диагностического SLERP-слияния. Объединяет сильные стороны двух моделей:
Модель собрана методом SLERP и не проходила дополнительного обучения после слияния.
Модель сохраняет uncensored-характер, однако при очень высокой температуре (0.8+) и большом top_k может изредка добавлять короткие дисклеймеры. Генерация не блокируется и продолжается после них.
</details>MN-12B-LucidFaun-RP-RU is a diagnostic SLERP merge combining the lively RP character of Faun with the stability and rich storytelling capabilities of lucid.
This model represents a surgical approach to merging. Instead of blending everything equally, we experimentally identified where Faun's censorship resides (late MLP layers) and replaced only those components with lucid.
The result is a model that:
Built using diagnostic SLERP merging with layer-specific weight distribution.
| Feature | Description |
|---|---|
| Languages | Russian, English |
| Censorship | Almost none (rare disclaimers at high temp) |
| Roleplay | Faun's lively character, lucid's stability |
| Story-Writing | Full lucid capabilities (scene planning, OOC, etc.) |
| Tool Calling | ✅ Fully supported |
| Context Length | Stable up to ~8192 tokens |
| Temperature Tolerance | Safe ≤0.5, up to 0.8 with top_k=20 |
| Architecture | Mistral Nemo 12B |
Experiment 1 — MLP vs Self-Attention
We discovered that censorship in Faun lives exclusively in MLP layers. Self-attention from Faun did not trigger refusals.
Experiment 2 — Localization within MLP
By applying gradient distributions across layers, we found censorship is concentrated in late MLP layers (layers ~25–40).
Final Configuration — Gradual Intervention
MLP weight of lucid increases toward the end: [0.1, 0.2, 0.5, 0.4, 0.75]
Self-attention is mixed 0.5 for stability while preserving Faun's character.
LayerNorm is mixed 0.5 for overall stability.
slices:
- sources:
- model: limloop/MN-12B-Faun-RP-RU
layer_range: [0, 40]
- model: dreamgen/lucid-v1-nemo
layer_range: [0, 40]
merge_method: slerp
base_model: limloop/MN-12B-Faun-RP-RU
parameters:
t:
- filter: self_attn
value: 0.5
- filter: mlp
value: [0.1, 0.2, 0.5, 0.4, 0.75]
- value: 0.5
dtype: bfloat16
tokenizer:
source: "base"
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_name = "limloop/MN-12B-LucidFaun-RP-RU"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map="auto"
)
prompt = "Ты — лесной фавн, говоришь загадками и любишь шалить."
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(
inputs,
max_new_tokens=512,
temperature=0.6,
top_k=30,
do_sample=True
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
Built using mergekit with SLERP (Spherical Linear Interpolation), which allows smooth interpolation between models while preserving geometric properties.
The merge uses a graduated approach for MLP layers, increasing lucid influence toward later layers where censorship was detected:
| Layer Zone (approx) | lucid weight (MLP) | Effect |
|---|---|---|
| 0–8 | 0.1 | Almost pure Faun (early patterns) |
| 8–16 | 0.2 | Slight lucid influence |
| 16–24 | 0.5 | Balanced |
| 24–32 | 0.4 | Slightly more Faun |
| 32–40 | 0.75 | Lucid dominates — removes censorship |
Self-attention is mixed evenly (0.5) to preserve character while adding stability.
LayerNorm is mixed 0.5 for overall stability.