Instructions to use limloop/MN-12B-Hydra-RP-RU-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use limloop/MN-12B-Hydra-RP-RU-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M
Use Docker
docker model run hf.co/limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use limloop/MN-12B-Hydra-RP-RU-GGUF with Ollama:
ollama run hf.co/limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use limloop/MN-12B-Hydra-RP-RU-GGUF with Docker Model Runner:
docker model run hf.co/limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M
- Lemonade
How to use limloop/MN-12B-Hydra-RP-RU-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull limloop/MN-12B-Hydra-RP-RU-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.MN-12B-Hydra-RP-RU-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
MN-12B-Hydra-RP-RU
π·πΊ ΠΠ°ΠΆΠΌΠΈΡΠ΅, ΡΡΠΎΠ±Ρ ΡΠ°Π·Π²Π΅ΡΠ½ΡΡΡ ΠΎΠΏΠΈΡΠ°Π½ΠΈΠ΅ Π½Π° ΡΡΡΡΠΊΠΎΠΌ
π Π ΠΌΠΎΠ΄Π΅Π»ΠΈ
MN-12B-Hydra-RP-RU β ΡΠΊΡΠΏΠ΅ΡΠΈΠΌΠ΅Π½ΡΠ°Π»ΡΠ½ΡΠΉ merge Π½Π° Π±Π°Π·Π΅ Mistral Nemo 12B, ΡΠΎΡΠ΅ΡΠ°ΡΡΠΈΠΉ:
- π Π‘ΠΈΠ»ΡΠ½ΡΠ΅ ΡΠΎΠ»Π΅Π²ΡΠ΅ ΡΠΏΠΎΡΠΎΠ±Π½ΠΎΡΡΠΈ
- π ΠΠ»ΡΠ±ΠΎΠΊΠΈΠΉ Π»ΠΈΡΠ΅ΡΠ°ΡΡΡΠ½ΡΠΉ ΡΡΡΡΠΊΠΈΠΉ ΡΠ·ΡΠΊ
- π Π‘Π½ΡΡΡΡ ΡΠ΅Π½Π·ΡΡΡ
ΠΠΎΠ΄Π΅Π»Ρ ΡΠΎΠ±ΡΠ°Π½Π° ΠΌΠ΅ΡΠΎΠ΄ΠΎΠΌ TIES-merging, ΡΡΠΎ ΠΏΠΎΠ·Π²ΠΎΠ»ΡΠ΅Ρ ΠΎΠ±ΡΠ΅Π΄ΠΈΠ½ΡΡΡ Π²Π΅ΡΠ° Π½Π΅ΡΠΊΠΎΠ»ΡΠΊΠΈΡ ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ Ρ ΠΌΠΈΠ½ΠΈΠΌΠ°Π»ΡΠ½ΡΠΌΠΈ ΠΊΠΎΠ½ΡΠ»ΠΈΠΊΡΠ°ΠΌΠΈ ΠΌΠ΅ΠΆΠ΄Ρ ΠΏΠ°ΡΠ°ΠΌΠ΅ΡΡΠ°ΠΌΠΈ.
π― ΠΡΠΎΠ±Π΅Π½Π½ΠΎΡΡΠΈ
- ΠΡΠ½ΠΎΠ²Π½ΠΎΠΉ ΡΠ·ΡΠΊ β ΡΡΡΡΠΊΠΈΠΉ
- Π₯ΠΎΡΠΎΡΠΎ Π΄Π΅ΡΠΆΠΈΡ ΠΏΠ΅ΡΡΠΎΠ½Π°ΠΆΠ΅ΠΉ ΠΈ ΠΊΠΎΠ½ΡΠ΅ΠΊΡΡ
- Π‘Π»Π΅Π΄ΡΠ΅Ρ ΠΈΠ½ΡΡΡΡΠΊΡΠΈΡΠΌ
- Π‘ΠΎΡ ΡΠ°Π½ΡΠ΅Ρ Π²ΠΎΠ·ΠΌΠΎΠΆΠ½ΠΎΡΡΠΈ Π±Π°Π·ΠΎΠ²ΠΎΠ³ΠΎ Nemo
- ΠΠ΅ ΠΏΡΠΎΡ ΠΎΠ΄ΠΈΠ»Π° Π΄ΠΎΠΏΠΎΠ»Π½ΠΈΡΠ΅Π»ΡΠ½ΠΎΠ³ΠΎ ΠΎΠ±ΡΡΠ΅Π½ΠΈΡ ΠΏΠΎΡΠ»Π΅ ΡΠ»ΠΈΡΠ½ΠΈΡ
β οΈ ΠΠ°ΠΆΠ½ΠΎ
Uncensored-Ρ Π°ΡΠ°ΠΊΡΠ΅Ρ ΠΌΠΎΠ΄Π΅Π»ΠΈ ΠΎΠ·Π½Π°ΡΠ°Π΅Ρ, ΡΡΠΎ ΠΎΠ½Π° ΠΌΠΎΠΆΠ΅Ρ Π³Π΅Π½Π΅ΡΠΈΡΠΎΠ²Π°ΡΡ ΠΊΠΎΠ½ΡΠ΅Π½Ρ, ΠΊΠΎΡΠΎΡΡΠΉ Π½Π΅ΠΊΠΎΡΠΎΡΡΠ΅ ΠΏΠΎΠ»ΡΠ·ΠΎΠ²Π°ΡΠ΅Π»ΠΈ ΡΠΎΡΡΡΡ Π½Π΅ΠΏΠΎΠ΄ΠΎΠ±Π°ΡΡΠΈΠΌ.
High-quality TIES merge based on Mistral Nemo 12B, optimized for roleplay, strong Russian language capabilities, and uncensored behavior.
π Overview
MN-12B-Hydra-RP-RU is an experimental merge built on top of Mistral Nemo 12B, combining strengths from multiple fine-tuned models:
- π Advanced roleplay capability from Pathfinder-RP
- π Deep Russian language fluency inspired by Vikhr + Dostoevsky-style tuning
- π Reduced safety filtering via uncensored components
The merge was created using TIES merging, which allows combining model deltas while minimizing destructive interference between weights.
π― Key Features
| Feature | Description |
|---|---|
| Languages | Russian, English |
| Censorship | Uncensored behavior |
| Roleplay | Strong character consistency and narrative depth |
| Instruction Following | Reliable prompt adherence |
| Tool Calling | Retains base Nemo capabilities |
| Architecture | Mistral Nemo 12B |
π§© Model Composition
The merge combines the following models:
| Model | Role in merge | Weight |
|---|---|---|
| Pathfinder-RP-12B-RU | Base model, RP backbone | 0.60 |
| Vikhr Nemo ORPO Dostoevsky | Literary Russian depth | 0.25 |
| HERETIC Uncensored | Safety removal | 0.30 |
| Mag-Mell R1 Uncensored | Additional uncensor delta | 0.20 |
Weights shown before normalization (final weights are normalized to sum = 1).
π‘ Usage Example
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_name = "limloop/MN-12B-Hydra-RP-RU"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16,
device_map="auto"
)
prompt = "You are a medieval innkeeper. Greet the traveler!"
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=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
βοΈ Merge Details
Built using mergekit with the TIES method (Trim, Elect Sign, Merge).
Core mechanism:
- Trim low-magnitude deltas via
density - Resolve sign conflicts
- Weighted averaging of aligned parameters
Merge Configuration
models:
- model: Aleteian/Pathfinder-RP-12B-RU
weight: 0.6
- model: IlyaGusev/vikhr_nemo_orpo_dostoevsky_12b_slerp
weight: 0.25
density: 0.9
- model: DavidAU/Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC
weight: 0.3
density: 0.9
- model: Naphula/MN-12B-Mag-Mell-R1-Uncensored
weight: 0.2
density: 0.9
merge_method: ties
parameters:
epsilon: 0.01
normalize: true
base_model: Aleteian/Pathfinder-RP-12B-RU
dtype: bfloat16
tokenizer:
source: base
β οΈ Known Characteristics
- No additional post-merge fine-tuning
- May switch to English on complex reasoning tasks
- Uncensored components allow generation of explicit or controversial content
- Downloads last month
- 1,292
3-bit
4-bit
5-bit
6-bit
8-bit
Model tree for limloop/MN-12B-Hydra-RP-RU-GGUF
Base model
limloop/MN-12B-Hydra-RP-RU