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

Pygmalion 2.7B by PygmalionAI

 »  All LLMs  »  PygmalionAI  »  Pygmalion 2.7B   URL Share it on

  2272   
  Autotrain compatible   Conversational   En   Gpt neo   Pytorch   Region:us   Tensorboard
Model Card on HF 🤗: https://huggingface.co/PygmalionAI/pygmalion-2.7b 

Pygmalion 2.7B Benchmarks

ARC: 32.76 vs 96.7 (so35)-66.1%
HellaSwag: 54.13 vs 95.3 (gpt4)-43.2%
MMLU: 23.28 vs 88.3 (so35)-73.6%
TruthfulQA: 37.17 vs 59 (gpt4)-37%
WinoGrande: 56.51 vs 87.5 (gpt4)-35.4%
LLME Score: 0.13893
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pygmalion 2.7B (PygmalionAI/pygmalion-2.7b)

Pygmalion 2.7B Parameters and Internals

Model Type 
text generation, dialogue model
Use Cases 
Areas:
Research
Applications:
Conversational AI, Text generation
Primary Use Cases:
Dialogue simulation, Character portrayal
Limitations:
Not suitable for minors due to potential X-rated content
Considerations:
Providing conversational context or example dialogues improves performance
Supported Languages 
en (full coverage)
Training Details 
Data Sources:
Multiple dialogue sources including real and machine-generated conversations
Data Volume:
~48.5 million tokens
Hardware Used:
4 NVIDIA A40 GPUs
Model Architecture:
Based on EleutherAI's GPT-Neo architecture
Input Output 
Input Format:
Prompt format with character persona and dialogue history
Accepted Modalities:
text
Output Format:
Dialogue response in text format
Performance Tips:
Adhere to input prompt format for optimal performance
LLM NamePygmalion 2.7B
Repository 🤗https://huggingface.co/PygmalionAI/pygmalion-2.7b 
Model Size2.7b
Required VRAM5.4 GB
Updated2025-02-05
MaintainerPygmalionAI
Model Typegpt_neo
Model Files  5.4 GB
Supported Languagesen
Model ArchitectureGPTNeoForCausalLM
Licensecreativeml-openrail-m
Context Length2048
Model Max Length2048
Transformers Version4.26.0.dev0
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size50257
Torch Data Typefloat16
Activation Functiongelu_new
Errorsreplace

Best Alternatives to Pygmalion 2.7B

Best Alternatives
Context / RAM
Downloads
Likes
ChildModel 022K / 5.3 GB50
PRIME2 Openai2K / 6.6 GB1051
GPT Neo 2.7B Lama2K / 10.6 GB50
EleutherAI GPT Neo 2.7B 4bits2K / 1.7 GB780
GPT Neo 2.7B2K / 10.7 GB207709464
... Style Transfer Using Examples2K / 5.4 GB191
Pygmalion 2.7B2K / 0 GB1091
GPT Neo 2.7B Horni2K / 6.6 GB820
GPT Neo 2.7B Shinen2K / 6.6 GB510
GPT Neo 2.7B Horni LN2K / 6.6 GB280
Note: green Score (e.g. "73.2") means that the model is better than PygmalionAI/pygmalion-2.7b.

Rank the Pygmalion 2.7B 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? 42577 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