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

Pythia 31M by ethzanalytics

 »  All LLMs  »  ethzanalytics  »  Pythia 31M   URL Share it on

  6   
  Autotrain compatible Base model:eleutherai/pythia-3... Base model:finetune:eleutherai...   Dataset:eleutherai/pile   En   Endpoints compatible   Gpt neox   Region:us   Safetensors   Smol
Model Card on HF 🤗: https://huggingface.co/ethzanalytics/pythia-31m 

Pythia 31M Benchmarks

ARC: 19.97 vs 96.7 (so35)-79.3%
HellaSwag: 26.34 vs 95.3 (gpt4)-72.4%
MMLU: 24.27 vs 88.3 (so35)-72.5%
TruthfulQA: 50.12 vs 59 (gpt4)-15.1%
WinoGrande: 49.09 vs 87.5 (gpt4)-43.9%
LLME Score: 0.155
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pythia 31M (ethzanalytics/pythia-31m)
🌟 Advertise your project 🚀

Pythia 31M Parameters and Internals

Model Type 
text-generation
Additional Notes 
This is a smaller version of the 'official' checkpoints included in the Pythia study and explicitly saved in fp32 to see safetensors params.
Supported Languages 
primary (en)
LLM NamePythia 31M
Repository 🤗https://huggingface.co/ethzanalytics/pythia-31m 
Base Model(s)  Pythia 31M   EleutherAI/pythia-31m
Model Size31m
Required VRAM0.1 GB
Updated2025-09-23
Maintainerethzanalytics
Model Typegpt_neox
Model Files  0.1 GB
Supported Languagesen
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.33.1
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50304
Torch Data Typefloat32

Best Alternatives to Pythia 31M

Best Alternatives
Context / RAM
Downloads
Likes
Pythia 31M Chat V12K / 0.1 GB138
...ia 31M Simplewiki Scratch Bf162K / 0.1 GB18500
...implepile Lite 2048 Scratch 2e2K / 0.1 GB18520
... Goodwiki Deduped 2048 Scratch2K / 0.1 GB18561
Pythia 31M KI V1 2048 Scratch2K / 0.1 GB8680
Pythia 31M2K / 0.1 GB799165
Pythia 31M Simplewiki 20482K / 0.1 GB6591
...31M SimpleRW Lite 2048 Scratch2K / 0.1 GB61
Note: green Score (e.g. "73.2") means that the model is better than ethzanalytics/pythia-31m.

Rank the Pythia 31M 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? 51611 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