MN-12B-Hydra-RP-RU

Original model

πŸ‡·πŸ‡Ί НаТмитС, Ρ‡Ρ‚ΠΎΠ±Ρ‹ Ρ€Π°Π·Π²Π΅Ρ€Π½ΡƒΡ‚ΡŒ описаниС Π½Π° русском

🌟 О модСли

MN-12B-Hydra-RP-RU β€” ΡΠΊΡΠΏΠ΅Ρ€ΠΈΠΌΠ΅Π½Ρ‚Π°Π»ΡŒΠ½Ρ‹ΠΉ merge Π½Π° Π±Π°Π·Π΅ Mistral Nemo 12B, ΡΠΎΡ‡Π΅Ρ‚Π°ΡŽΡ‰ΠΈΠΉ:

  • 🎭 Π‘ΠΈΠ»ΡŒΠ½Ρ‹Π΅ Ρ€ΠΎΠ»Π΅Π²Ρ‹Π΅ способности
  • πŸ“š Π“Π»ΡƒΠ±ΠΎΠΊΠΈΠΉ Π»ΠΈΡ‚Π΅Ρ€Π°Ρ‚ΡƒΡ€Π½Ρ‹ΠΉ русский язык
  • πŸ”“ Π‘Π½ΡΡ‚ΡƒΡŽ Ρ†Π΅Π½Π·ΡƒΡ€Ρƒ

МодСль собрана ΠΌΠ΅Ρ‚ΠΎΠ΄ΠΎΠΌ TIES-merging, Ρ‡Ρ‚ΠΎ позволяСт ΠΎΠ±ΡŠΠ΅Π΄ΠΈΠ½ΡΡ‚ΡŒ вСса Π½Π΅ΡΠΊΠΎΠ»ΡŒΠΊΠΈΡ… ΠΌΠΎΠ΄Π΅Π»Π΅ΠΉ с ΠΌΠΈΠ½ΠΈΠΌΠ°Π»ΡŒΠ½Ρ‹ΠΌΠΈ ΠΊΠΎΠ½Ρ„Π»ΠΈΠΊΡ‚Π°ΠΌΠΈ ΠΌΠ΅ΠΆΠ΄Ρƒ ΠΏΠ°Ρ€Π°ΠΌΠ΅Ρ‚Ρ€Π°ΠΌΠΈ.

🎯 ΠžΡΠΎΠ±Π΅Π½Π½ΠΎΡΡ‚ΠΈ

  • Основной язык β€” русский
  • Π₯ΠΎΡ€ΠΎΡˆΠΎ Π΄Π΅Ρ€ΠΆΠΈΡ‚ пСрсонаТСй ΠΈ контСкст
  • Π‘Π»Π΅Π΄ΡƒΠ΅Ρ‚ инструкциям
  • БохраняСт возмоТности Π±Π°Π·ΠΎΠ²ΠΎΠ³ΠΎ Nemo
  • НС ΠΏΡ€ΠΎΡ…ΠΎΠ΄ΠΈΠ»Π° Π΄ΠΎΠΏΠΎΠ»Π½ΠΈΡ‚Π΅Π»ΡŒΠ½ΠΎΠ³ΠΎ обучСния послС слияния

⚠️ Π’Π°ΠΆΠ½ΠΎ

Uncensored-Ρ…Π°Ρ€Π°ΠΊΡ‚Π΅Ρ€ ΠΌΠΎΠ΄Π΅Π»ΠΈ ΠΎΠ·Π½Π°Ρ‡Π°Π΅Ρ‚, Ρ‡Ρ‚ΠΎ ΠΎΠ½Π° ΠΌΠΎΠΆΠ΅Ρ‚ Π³Π΅Π½Π΅Ρ€ΠΈΡ€ΠΎΠ²Π°Ρ‚ΡŒ ΠΊΠΎΠ½Ρ‚Π΅Π½Ρ‚, ΠΊΠΎΡ‚ΠΎΡ€Ρ‹ΠΉ Π½Π΅ΠΊΠΎΡ‚ΠΎΡ€Ρ‹Π΅ ΠΏΠΎΠ»ΡŒΠ·ΠΎΠ²Π°Ρ‚Π΅Π»ΠΈ сочтут Π½Π΅ΠΏΠΎΠ΄ΠΎΠ±Π°ΡŽΡ‰ΠΈΠΌ.

High-quality TIES merge based on Mistral Nemo 12B, optimized for roleplay, strong Russian language capabilities, and uncensored behavior.


🌍 Overview

MN-12B-Hydra-RP-RU is an experimental merge built on top of Mistral Nemo 12B, combining strengths from multiple fine-tuned models:

  • 🎭 Advanced roleplay capability from Pathfinder-RP
  • πŸ“š Deep Russian language fluency inspired by Vikhr + Dostoevsky-style tuning
  • πŸ”“ Reduced safety filtering via uncensored components

The merge was created using TIES merging, which allows combining model deltas while minimizing destructive interference between weights.


🎯 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

🧩 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).


πŸ’‘ 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)

βš™οΈ Merge Details

Built using mergekit with the TIES method (Trim, Elect Sign, Merge).

Core mechanism:

  1. Trim low-magnitude deltas via density
  2. Resolve sign conflicts
  3. 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

⚠️ 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
GGUF
Model size
12B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for limloop/MN-12B-Hydra-RP-RU-GGUF

Quantized
(3)
this model

Collection including limloop/MN-12B-Hydra-RP-RU-GGUF