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

Pygmalion 2 13B by PygmalionAI

 »  All LLMs  »  PygmalionAI  »  Pygmalion 2 13B   URL Share it on

  1153   
  Autotrain compatible Dataset:databricks/databricks-... Dataset:jondurbin/airoboros-gp... Dataset:norquinal/claude multi...   Dataset:open-orca/openorca   Dataset:pygmalionai/pippa   En   Instruct   Llama   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/PygmalionAI/pygmalion-2-13b 

Pygmalion 2 13B Benchmarks

ARC: 60.32 vs 96.7 (so35)-37.6%
HellaSwag: 82.37 vs 95.3 (gpt4)-13.6%
MMLU: 56.02 vs 88.3 (so35)-36.6%
TruthfulQA: 42.22 vs 59 (gpt4)-28.4%
WinoGrande: 78.06 vs 87.5 (gpt4)-10.8%
GSM8K: 11.75 vs 96.4 (so35)-87.8%
LLME Score: 0.16054
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pygmalion 2 13B (PygmalionAI/pygmalion-2-13b)

Pygmalion 2 13B Parameters and Internals

Model Type 
text generation, instruct
Use Cases 
Areas:
fictional writing for entertainment purposes
Limitations:
Not fine-tuned to be safe and harmless, May produce socially unacceptable or undesirable text, Outputs might often be factually wrong or misleading
Additional Notes 
The model is biased towards fiction writing and conversation. It was known as Metharme and aimed for roles involving conversation, roleplaying, and storywriting that can be guided using natural language.
Supported Languages 
English (High)
Training Details 
Data Sources:
PygmalionAI/PIPPA, Open-Orca/OpenOrca, Norquinal/claude_multiround_chat_30k, jondurbin/airoboros-gpt4-1.4.1, databricks/databricks-dolly-15k
Methodology:
Supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories and conversations with synthetically generated instructions attached.
Input Output 
Input Format:
<|system|>, <|user|>, <|model|> prompts
Accepted Modalities:
text
LLM NamePygmalion 2 13B
Repository 🤗https://huggingface.co/PygmalionAI/pygmalion-2-13b 
Model Size13b
Required VRAM26 GB
Updated2025-06-01
MaintainerPygmalionAI
Model Typellama
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3   9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.33.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Pygmalion 2 13B

Model
Likes
Downloads
VRAM
Pygmalion 2 13B GGUF2919055 GB
Pygmalion 2 13B AWQ64887 GB
Pygmalion 2 13B GPTQ422087 GB

Best Alternatives to Pygmalion 2 13B

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 13B Instruct Hf16K / 26 GB220345146
NexusRaven V2 13B16K / 26 GB2999466
CodeLlama 13B MORepair16K / 26 GB162
CodeLlama 13B Instruct Hf16K / 26 GB231221
TableLLM 13B16K / 26 GB73828
NexusRaven 13B16K / 26 GB42103
Panda Coder 13B16K / 26 GB5313
... Llama 2 13B Instruct Text2sql16K / 26 GB6627
Gen Sim16K / 0.3 GB232
Llama 3 13B Instruct Ft8K / 26.1 GB382
Note: green Score (e.g. "73.2") means that the model is better than PygmalionAI/pygmalion-2-13b.

Rank the Pygmalion 2 13B 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? 47753 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