Instructions to use limloop/MN-12B-LucidFaun-RP-RU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use limloop/MN-12B-LucidFaun-RP-RU with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="limloop/MN-12B-LucidFaun-RP-RU") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("limloop/MN-12B-LucidFaun-RP-RU") model = AutoModelForCausalLM.from_pretrained("limloop/MN-12B-LucidFaun-RP-RU", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use limloop/MN-12B-LucidFaun-RP-RU with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "limloop/MN-12B-LucidFaun-RP-RU" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "limloop/MN-12B-LucidFaun-RP-RU", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/limloop/MN-12B-LucidFaun-RP-RU
- SGLang
How to use limloop/MN-12B-LucidFaun-RP-RU with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "limloop/MN-12B-LucidFaun-RP-RU" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "limloop/MN-12B-LucidFaun-RP-RU", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "limloop/MN-12B-LucidFaun-RP-RU" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "limloop/MN-12B-LucidFaun-RP-RU", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use limloop/MN-12B-LucidFaun-RP-RU with Docker Model Runner:
docker model run hf.co/limloop/MN-12B-LucidFaun-RP-RU
MN-12B-LucidFaun-RP-RU
๐ท๐บ ะะฐะถะผะธัะต, ััะพะฑั ัะฐะทะฒะตัะฝััั ะพะฟะธัะฐะฝะธะต ะฝะฐ ััััะบะพะผ
๐ ะ ะผะพะดะตะปะธ
MN-12B-LucidFaun-RP-RU โ ะณะธะฑัะธะดะฝะฐั ะผะพะดะตะปั ะฝะฐ ะฑะฐะทะต Mistral Nemo 12B, ัะพะทะดะฐะฝะฝะฐั ะผะตัะพะดะพะผ ะดะธะฐะณะฝะพััะธัะตัะบะพะณะพ SLERP-ัะปะธัะฝะธั. ะะฑัะตะดะธะฝัะตั ัะธะปัะฝัะต ััะพัะพะฝั ะดะฒัั ะผะพะดะตะปะตะน:
- ๐ญ ะะธะฒะพะน RP-ั ะฐัะฐะบัะตั Faun โ ัะพะฒัะตะผะตะฝะฝัะน ััะธะปั, ะฑะพะณะฐัะฐั ะปะตะบัะธะบะฐ, ะฟะพะดะดะตัะถะบะฐ ninja-ัะพัะผะฐัะฐ ะธะฝััััะบัะธะน ะธ tool calling
- ๐ ะกัะฐะฑะธะปัะฝะพััั ะธ ะดะตัะฐะปะธะทะฐัะธั lucid โ ะฟัะตะฒะพัั ะพะดะฝะพะต ะบะฐัะตััะฒะพ ััะพัะธัะตะปะปะธะฝะณะฐ, ัััะพะนัะธะฒะพััั ะฝะฐ ะดะปะธะฝะฝัั ะบะพะฝัะตะบััะฐั , ะพััััััะฒะธะต ัะตะฝะทััั
- ๐ฌ ะขะพัะตัะฝะพะต ะธัะฟัะฐะฒะปะตะฝะธะต โ ัะตะฝะทััะฐ Faun ะปะพะบะฐะปะธะทะพะฒะฐะฝะฐ ะฒ ะฟะพะทะดะฝะธั MLP-ัะปะพัั ะธ ะทะฐะผะตะฝะตะฝะฐ ะฝะฐ lucid
ะะพะดะตะปั ัะพะฑัะฐะฝะฐ ะผะตัะพะดะพะผ SLERP ะธ ะฝะต ะฟัะพั ะพะดะธะปะฐ ะดะพะฟะพะปะฝะธัะตะปัะฝะพะณะพ ะพะฑััะตะฝะธั ะฟะพัะปะต ัะปะธัะฝะธั.
๐ฏ ะัะพะฑะตะฝะฝะพััะธ
- ะัะฐะบัะธัะตัะบะธ ะฟะพะปะฝะพะต ะพััััััะฒะธะต ัะตะฝะทััั โ ัะตะดะบะธะต ะดะธัะบะปะตะนะผะตัั ะฒะพะทะผะพะถะฝั ัะพะปัะบะพ ะฟัะธ ะฒััะพะบะพะน ัะตะผะฟะตัะฐัััะต
- ะฃะปัััะตะฝะฝะฐั ััะฐะฑะธะปัะฝะพััั โ ะฟัะตะฒะพัั ะพะดะธั Faun ะฟัะธ temperature โค0.5, ัะฐะฑะพัะฐะตั ั 0.8 ะฟัะธ top_k=20
- Tool calling โ ะฟะพะปะฝะพัััั ะฟะพะดะดะตัะถะธะฒะฐะตััั
- ะะพะฝัะตะบัั โ ััะฐะฑะธะปัะฝะพ ัะฐะฑะพัะฐะตั ะดะพ 8192 ัะพะบะตะฝะพะฒ (ะฟัะพะฒะตัะตะฝะพ)
- ะ ัััะบะธะน ัะทัะบ โ ัะพั ัะฐะฝะธะปัั ะธ ะฒะทะผะพะถะฝะพ ัะปัััะตะฝ ะทะฐ ััะตั ัะปะธัะฝะธั ั lucid
- ะคะพัะผะฐั ะธะฝััััะบัะธะน โ ัะพั ัะฐะฝะธะปัั ะพั Faun
- ะกัะพัะธัะตะปะปะธะฝะณ โ ัะฝะฐัะปะตะดะพะฒะฐะป ะฑะพะณะฐััะต ะฒะพะทะผะพะถะฝะพััะธ lucid ะฟะพ ะฟะปะฐะฝะธัะพะฒะฐะฝะธั ััะตะฝ, ัะฟัะฐะฒะปะตะฝะธั ััะถะตัะพะผ ะธ ัะฐะฑะพัะต ั ะฟะตััะพะฝะฐะถะฐะผะธ
โ ๏ธ ะะฐะถะฝะพ
ะะพะดะตะปั ัะพั ัะฐะฝัะตั uncensored-ั ะฐัะฐะบัะตั, ะพะดะฝะฐะบะพ ะฟัะธ ะพัะตะฝั ะฒััะพะบะพะน ัะตะผะฟะตัะฐัััะต (0.8+) ะธ ะฑะพะปััะพะผ top_k ะผะพะถะตั ะธะทัะตะดะบะฐ ะดะพะฑะฐะฒะปััั ะบะพัะพัะบะธะต ะดะธัะบะปะตะนะผะตัั. ะะตะฝะตัะฐัะธั ะฝะต ะฑะปะพะบะธััะตััั ะธ ะฟัะพะดะพะปะถะฐะตััั ะฟะพัะปะต ะฝะธั .
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.
๐ Overview
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:
- Keeps Faun's personality, style, and tool calling
- Gains lucid's stability, rich prose, and uncensored behavior
- Inherits lucid's advanced storytelling features
- Maintains coherence even on long contexts
Built using diagnostic SLERP merging with layer-specific weight distribution.
๐ฏ Key Features
| 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 | โ Fully supported |
| Context Length | Stable up to ~8192 tokens |
| Temperature Tolerance | Safe โค0.5, up to 0.8 with top_k=20 |
| Architecture | Mistral Nemo 12B |
๐งช Methodology: Why This Merge Works
Diagnostic Approach
Experiment 1 โ 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 โ Localization within MLP
By applying gradient distributions across layers, we found censorship is concentrated in late MLP layers (layers ~25โ40).Final Configuration โ 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.
Merge Configuration
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"
๐ก Usage Examples
Basic Usage
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 = "ะขั โ ะปะตัะฝะพะน ัะฐะฒะฝ, ะณะพะฒะพัะธัั ะทะฐะณะฐะดะบะฐะผะธ ะธ ะปัะฑะธัั ัะฐะปะธัั."
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)
โ๏ธ Merge Details
Built using mergekit with SLERP (Spherical Linear Interpolation), which allows smooth interpolation between models while preserving geometric properties.
Layer-Specific Weights
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 |
|---|---|---|
| 0โ8 | 0.1 | Almost pure Faun (early patterns) |
| 8โ16 | 0.2 | Slight lucid influence |
| 16โ24 | 0.5 | Balanced |
| 24โ32 | 0.4 | Slightly more Faun |
| 32โ40 | 0.75 | Lucid dominates โ removes censorship |
Self-attention is mixed evenly (0.5) to preserve character while adding stability.
LayerNorm is mixed 0.5 for overall stability.
- Downloads last month
- 59