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

Psyonic Cetacean V1 20B Ultra Quality Float32 by DavidAU

 »  All LLMs  »  DavidAU  »  Psyonic Cetacean V1 20B Ultra Quality Float32   URL Share it on

  34   
  32 bit upscale   Autotrain compatible   En   Endpoints compatible   Full 32 bit precision   Llama   Master files   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/DavidAU/Psyonic-Cetacean-V1-20B-Ultra-Quality-Float32 

Psyonic Cetacean V1 20B Ultra Quality Float32 Benchmarks

LLME Score: 0.19084
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Psyonic Cetacean V1 20B Ultra Quality Float32 (DavidAU/Psyonic-Cetacean-V1-20B-Ultra-Quality-Float32)

Psyonic Cetacean V1 20B Ultra Quality Float32 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Greater distance between each quant in precision remaster with larger output differences.
Supported Languages 
en (English)
Input Output 
Input Format:
F32 output format for best results.
Accepted Modalities:
text
Output Format:
32 bit upscale outputs with greater precision.
Performance Tips:
Longer prompts may not be needed due to precision upscale.
LLM NamePsyonic Cetacean V1 20B Ultra Quality Float32
Repository 🤗https://huggingface.co/DavidAU/Psyonic-Cetacean-V1-20B-Ultra-Quality-Float32 
Model Size20b
Required VRAM80.1 GB
Updated2025-02-22
MaintainerDavidAU
Model Typellama
Model Files  7.8 GB: 1-of-11   7.9 GB: 2-of-11   7.8 GB: 3-of-11   7.9 GB: 4-of-11   7.9 GB: 5-of-11   7.9 GB: 6-of-11   7.8 GB: 7-of-11   7.9 GB: 8-of-11   7.9 GB: 9-of-11   7.9 GB: 10-of-11   1.4 GB: 11-of-11
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.42.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Psyonic Cetacean V1 20B Ultra Quality Float32

Best Alternatives
Context / RAM
Downloads
Likes
Internlm2 5 20B Llamafied256K / 39.9 GB1303
Internlm2 20B Llama32K / 39.6 GB174820
Stellaris Internlm2 20B R51232K / 39.8 GB133
Internlm2 Base 20B Llama32K / 39.6 GB233
Internlm2 Chat 20B Llama Old32K / 39.6 GB183
Internlm2 Base 20B Llama32K / 39.6 GB140
Deita 20B32K / 39.8 GB491
Bagel 20B V04 Llama32K / 39.6 GB147
Bagel DPO 20B V04 Llama32K / 39.6 GB173
Internlm2 Limarp Chat 20B32K / 39.6 GB122
Note: green Score (e.g. "73.2") means that the model is better than DavidAU/Psyonic-Cetacean-V1-20B-Ultra-Quality-Float32.

Rank the Psyonic Cetacean V1 20B Ultra Quality Float32 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