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

Pantheon RP 1.6.2 22B Small by Gryphe

 »  All LLMs  »  Gryphe  »  Pantheon RP 1.6.2 22B Small   URL Share it on

  40   
  Axolotl Base model:finetune:mistralai/... Base model:mistralai/mistral-s...   Chatml   En   Finetuned   Instruct   Mistral   Region:us   Roleplay   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Gryphe/Pantheon-RP-1.6.2-22b-Small 

Pantheon RP 1.6.2 22B Small Benchmarks

LLME Score: 0.22683
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pantheon RP 1.6.2 22B Small (Gryphe/Pantheon-RP-1.6.2-22b-Small)

Pantheon RP 1.6.2 22B Small Parameters and Internals

Model Type 
roleplay, chat
Use Cases 
Areas:
roleplay, chat
Applications:
general roleplay experience enhancement, persona creation
Limitations:
Relies heavily on correct input structure for optimal performance
Additional Notes 
Switching to a 12B model allowed for expanding the Pantheon personas without harming performance.
Supported Languages 
languages_supported (en), proficiency (unknown)
Training Details 
Data Sources:
SlimOrca Sonnet dataset, Sonnet 3.5 Pantheon-styled generic roleplay dataset, Sonnet 3.5 Pantheon Persona dataset, ChatGPT 4-o Pantheon subset, Opus Writing Prompts, Lyra the Assistant
Methodology:
Fine-tuning using a diverse mix of datasets, with 50/50 Asterisk/Narrative style
Hardware Used:
16GB GPU
Input Output 
Input Format:
Mistral prompt format
Accepted Modalities:
text
Performance Tips:
Use character name prompts and provide detailed descriptive contexts for optimal results.
Release Notes 
Version:
1.6.2
Notes:
Introduced a new base model Mistral Small. Added a small subset of OpenAI Pantheon Persona data generated using chatgpt-4o-latest model.
LLM NamePantheon RP 1.6.2 22B Small
Repository 🤗https://huggingface.co/Gryphe/Pantheon-RP-1.6.2-22b-Small 
Base Model(s)  Mistral Small Instruct 2409   mistralai/Mistral-Small-Instruct-2409
Model Size22b
Required VRAM44.7 GB
Updated2025-02-22
MaintainerGryphe
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-9   5.0 GB: 2-of-9   5.0 GB: 3-of-9   4.9 GB: 4-of-9   5.0 GB: 5-of-9   5.0 GB: 6-of-9   4.9 GB: 7-of-9   5.0 GB: 8-of-9   5.0 GB: 9-of-9
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.45.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token[control_748]
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Pantheon RP 1.6.2 22B Small

Best Alternatives
Context / RAM
Downloads
Likes
MS Schisandra 22B V0.2128K / 44.7 GB409
...ntheon RP Pure 1.6.2 22B Small128K / 44.7 GB12827
MS Meadowlark 22B128K / 44.7 GB12513
... V4x1.6.2RP Cydonia VXXX 22B 8128K / 44.7 GB3055
... V4x1.6.2RP Cydonia VXXX 22B 6128K / 44.7 GB2862
Beeper King 22B128K / 44.7 GB317
MS Moingooistral 2409 22B128K / 44.7 GB340
MS Dampf 2409 22B128K / 44.7 GB280
MS A Coolyte 2409 22B128K / 44.7 GB280
MS Fujin 2409 22B128K / 44.7 GB270
Note: green Score (e.g. "73.2") means that the model is better than Gryphe/Pantheon-RP-1.6.2-22b-Small.

Rank the Pantheon RP 1.6.2 22B Small 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? 43470 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