LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Pantheon RP 1.6 12B Nemo KTO by Gryphe

 »  All LLMs  »  Gryphe  »  Pantheon RP 1.6 12B Nemo KTO   URL Share it on

  10   

Pantheon RP 1.6 12B Nemo KTO is an open-source language model by Gryphe. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, License: apache-2.0, LLM Explorer Score: 0.21.

  Axolotl Base model:finetune:mistralai/... Base model:mistralai/mistral-n...   Chatml   En   Finetuned   Instruct   Mistral   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Gryphe/Pantheon-RP-1.6-12b-Nemo-KTO 

Pantheon RP 1.6 12B Nemo KTO Benchmarks

MMLU Pro: 26.46
GPQA: 6.04
MUSR: 12.17
BBH: 33.03
IFEval: 46.36 vs 88 (so35)-47.3%
MATH Lvl 5: 5.29
LLME Score: 0.21352
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pantheon RP 1.6 12B Nemo KTO (Gryphe/Pantheon-RP-1.6-12b-Nemo-KTO)
🌟 Advertise your project 🚀

Pantheon RP 1.6 12B Nemo KTO Parameters and Internals

Model Type 
instruct, finetune, roleplay
Additional Notes 
Character names were added during training to improve roleplay interactions.
Supported Languages 
en (English)
Training Details 
Data Sources:
Deduped Sonnet 3.5 SlimOrca dataset, Pantheon Roleplay dataset
Methodology:
Multi-stage finetuning including KTO preference training.
Input Output 
Input Format:
ChatML prompt format.
Accepted Modalities:
text
Performance Tips:
Experiment with temperatures to find the best setting.
Release Notes 
Version:
1.6
Notes:
The final finetune now consists of data that is equally split between Markdown and novel-style roleplay. The base was redone. Select Claude-specific phrases were rewritten. Aiva no longer serves as both persona and assistant, with the assistant role given to Lyra. Stella's dialogue received some post-fix alterations.
LLM NamePantheon RP 1.6 12B Nemo KTO
Repository 🤗https://huggingface.co/Gryphe/Pantheon-RP-1.6-12b-Nemo-KTO 
Base Model(s)  Mistral Nemo Base 2407   mistralai/Mistral-Nemo-Base-2407
Model Size12b
Required VRAM24.5 GB
Updated2026-03-29
MaintainerGryphe
Model Typemistral
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.44.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Pantheon RP 1.6 12B Nemo KTO

Best Alternatives
Context / RAM
Downloads
Likes
Celestial Queen 12B1000K / 24.5 GB3058
Celestial Queen 12B Heretic1000K / 24.5 GB333
MN 12B Mag Mell R11000K / 24.5 GB1458236
Captain Eris Violet V0.420 12B1000K / 24.5 GB200354
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB2844138
...s PersonalityEngine V1.1.0 12B1000K / 24.5 GB65145
Captain Eris BMO Violent 12B1000K / 24.5 GB3052
Dans SakuraKaze V1.0.0 12B1000K / 24.5 GB1120
Impish Nemo 12B1000K / 24.5 GB207870
...n Eris BMO Violent GRPO V0.4201000K / 24.5 GB923
Note: green Score (e.g. "73.2") means that the model is better than Gryphe/Pantheon-RP-1.6-12b-Nemo-KTO.

Rank the Pantheon RP 1.6 12B Nemo KTO Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer