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

Nautilus RP 18B V2 by ParasiticRogue

 »  All LLMs  »  ParasiticRogue  »  Nautilus RP 18B V2   URL Share it on

  18   
  Merged Model   Autotrain compatible Base model:intervitens/mini-ma... Base model:mistralai/mistral-n... Base model:nbeerbower/lyra-gut... Base model:nbeerbower/mistral-... Base model:nbeerbower/mistral-... Base model:nbeerbower/mistral-... Base model:sao10k/mn-12b-lyra-...   Conversational   Endpoints compatible   Instruct   Mistral   Not-for-all-audiences   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ParasiticRogue/Nautilus-RP-18B-v2 

Nautilus RP 18B V2 Benchmarks

LLME Score: 0.19772
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nautilus RP 18B V2 (ParasiticRogue/Nautilus-RP-18B-v2)

Nautilus RP 18B V2 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
creative writing, roleplay
Applications:
chatbots, narrative generation, gaming
Primary Use Cases:
creative and detailed prose generation, maintaining character dynamics during interactions
Limitations:
Not for all audiences due to potentially explicit content
Considerations:
Ensure intended use aligns with ethical guidelines and non-commercial license stipulations.
Additional Notes 
This model represents a beta version with promising improvements in application settings for text generation and roleplay scenarios.
Training Details 
Methodology:
Frankenmerge using existing models like Nemo-Instruct, Mini-Magnum, Lyra-v1, and some DPO/ORPO variants; focused on improving prose quality through structured merging phases.
Input Output 
Input Format:
Nemo-Mistral formatting for prompts
Accepted Modalities:
text
Output Format:
Autonomous entity responses in chat format
Performance Tips:
Consider using specified prompt and system settings to optimize character and narrative engagement.
LLM NameNautilus RP 18B V2
Repository 🤗https://huggingface.co/ParasiticRogue/Nautilus-RP-18B-v2 
Base Model(s)  Mistral Nemo Bophades 12B   Mistral Nemo Gutades 12B   Mistral Nemo Gutenberg 12B V3   ...yra Gutenberg Mistral Nemo 12B   Mistral Nemo Instruct 2407   intervitens/mini-magnum-12b-v1.1   MN 12B Lyra V1   nbeerbower/mistral-nemo-bophades-12B   nbeerbower/mistral-nemo-gutades-12B   nbeerbower/mistral-nemo-gutenberg-12B-v3   nbeerbower/Lyra-Gutenberg-mistral-nemo-12B   mistralai/Mistral-Nemo-Instruct-2407   intervitens/mini-magnum-12b-v1.1   Sao10K/MN-12B-Lyra-v1
Merged ModelYes
Model Size12b
Required VRAM36.5 GB
Updated2024-12-02
MaintainerParasiticRogue
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-8   4.9 GB: 2-of-8   4.9 GB: 3-of-8   4.9 GB: 4-of-8   4.9 GB: 5-of-8   4.9 GB: 6-of-8   4.9 GB: 7-of-8   2.2 GB: 8-of-8
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length1024000
Model Max Length1024000
Transformers Version4.44.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Nautilus RP 18B V2

Best Alternatives
Context / RAM
Downloads
Likes
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB408188119
SauerkrautLM Nemo 12B Instruct1000K / 24.5 GB344322
Francois PE V2 Huali 12B1000K / 24.5 GB26913
MN Slush1000K / 24.5 GB16528
Mistral Nemo Wissenschaft 12B1000K / 24.5 GB7448
Magnum V4 12B1000K / 24.5 GB22342
ChatWaifu V1.41000K / 24.5 GB13219
ChatWaifu 12B V2.01000K / 24.5 GB6521
Mistral Nemo Bophades 12B1000K / 24.5 GB479
...gaMaid DarkWay FinalNoctis 12B1000K / 24.5 GB210
Note: green Score (e.g. "73.2") means that the model is better than ParasiticRogue/Nautilus-RP-18B-v2.

Rank the Nautilus RP 18B V2 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? 47770 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.
Release v20241227
  Support LLM Explorer