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

Calypso 3B Alpha V2 by Xilabs

 »  All LLMs  »  Xilabs  »  Calypso 3B Alpha V2   URL Share it on

  1859   
  Autotrain compatible   Dataset:xilabs/pippa-alpaca   En   Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Xilabs/calypso-3b-alpha-v2 

Calypso 3B Alpha V2 Benchmarks

ARC: 41.55 vs 96.7 (so35)-57%
HellaSwag: 71.48 vs 95.3 (gpt4)-25%
MMLU: 25.82 vs 88.3 (so35)-70.8%
TruthfulQA: 35.73 vs 59 (gpt4)-39.4%
WinoGrande: 65.27 vs 87.5 (gpt4)-25.4%
GSM8K: 0.68 vs 96.4 (so35)-99.3%
LLME Score: 0.15891
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Calypso 3B Alpha V2 (Xilabs/calypso-3b-alpha-v2)
🌟 Advertise your project 🚀

Calypso 3B Alpha V2 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
role-playing, one-on-one chatting
Limitations:
May produce content that is unsafe for all audiences, including inappropriate, offensive, or sensitive content., Responses may not be factually accurate and should not be relied upon for accurate information, especially in critical contexts., Might exhibit biases present in the training data.
Additional Notes 
Future iterations will focus on enhancing safety, improving factual accuracy, and reducing biases.
Supported Languages 
en (Intermediate)
Training Details 
Data Sources:
Xilabs/PIPPA-alpaca, private dataset of human-generated chats
Methodology:
Finetuning on the PIPPA-Alpaca dataset and a private dataset of human-generated chats.
LLM NameCalypso 3B Alpha V2
Repository 🤗https://huggingface.co/Xilabs/calypso-3b-alpha-v2 
Model Size3b
Required VRAM13.8 GB
Updated2025-08-22
MaintainerXilabs
Model Typellama
Model Files  3.0 GB: 1-of-5   3.0 GB: 2-of-5   3.0 GB: 3-of-5   3.0 GB: 4-of-5   1.8 GB: 5-of-5
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Calypso 3B Alpha V2

Best Alternatives
Context / RAM
Downloads
Likes
ISA 03 Mini 3B Hybrid Preview256K / 6.5 GB10664
Llama 3.2 3B Instruct128K / 6.5 GB19597331671
Llama 3.2 3B128K / 6.5 GB341655619
DeepSeek R1 Distill Llama 3B128K / 6.5 GB120316
Discord Micae Hermes 3 3B128K / 6.5 GB20322
Hermes 3 Llama 3.2 3B128K / 6.5 GB7989170
Llama 3.2 3B RP Toxic Fuse128K / 6.4 GB362
Orpheus 3B 0.1 Ft128K / 6.6 GB348407
Calme 3.1 Llamaloi 3B128K / 10.6 GB23701
Llama 3.2 3B128K / 6.5 GB29360
Note: green Score (e.g. "73.2") means that the model is better than Xilabs/calypso-3b-alpha-v2.

Rank the Calypso 3B Alpha 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? 50835 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 v20241124
  Support LLM Explorer