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

Pythia 2.8B Deduped by EleutherAI

 »  All LLMs  »  EleutherAI  »  Pythia 2.8B Deduped   URL Share it on

  5643   

Pythia 2.8B Deduped is an open-source language model by EleutherAI. Features: 2.8b LLM, VRAM: 5.7GB, Context: 2K, License: apache-2.0, HF Score: 36.7, LLM Explorer Score: 0.13, Arc: 36.3, HellaSwag: 60.7, MMLU: 26.8, TruthfulQA: 35.6, WinoGrande: 60.2, GSM8K: 0.8.

  Arxiv:2101.00027   Arxiv:2201.07311   Arxiv:2304.01373   Autotrain compatible Dataset:eleutherai/the pile de...   En   Endpoints compatible   Gpt neox   Pythia   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/EleutherAI/pythia-2.8b-deduped 

Pythia 2.8B Deduped Benchmarks

ARC: 36.26 vs 96.7 (so35)-62.5%
HellaSwag: 60.66 vs 95.3 (gpt4)-36.3%
MMLU: 26.78 vs 88.3 (so35)-69.7%
TruthfulQA: 35.56 vs 59 (gpt4)-39.7%
WinoGrande: 60.22 vs 87.5 (gpt4)-31.2%
GSM8K: 0.83 vs 96.4 (so35)-99.1%
LLME Score: 0.1262
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pythia 2.8B Deduped (EleutherAI/pythia-2.8b-deduped)
🌟 Advertise your project 🚀

Pythia 2.8B Deduped Parameters and Internals

Model Type 
Transformer-based Language Model
Use Cases 
Areas:
Research
Applications:
Interpretability research
Primary Use Cases:
Scientific experiments on language models, Promoting interpretability research
Limitations:
Not suitable for deployment, Not suitable for translation or generating text in languages other than English
Considerations:
Please conduct your own risk and bias assessment when applying the model.
Additional Notes 
Please note that all models in the *Pythia* suite were renamed in January 2023.
Training Details 
Data Sources:
EleutherAI/the_pile_deduplicated
LLM NamePythia 2.8B Deduped
Repository 🤗https://huggingface.co/EleutherAI/pythia-2.8b-deduped 
Model Size2.8b
Required VRAM5.7 GB
Updated2025-09-23
MaintainerEleutherAI
Model Typegpt_neox
Model Files  5.7 GB   5.7 GB
Supported Languagesen
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.24.0
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50304
Torch Data Typefloat16

Quantized Models of the Pythia 2.8B Deduped

Model
Likes
Downloads
VRAM
Pythia 2.8B Deduped GPTQ071 GB

Best Alternatives to Pythia 2.8B Deduped

Best Alternatives
Context / RAM
Downloads
Likes
Statichh Pythia 2.8B Sft Bf162K / 11.1 GB520
Pythia 2.8B Thai Base V12K / 5.9 GB52
Hh Full2K / 11.1 GB50
... Llm Pythia 2.8B Pm Gen Ian Nd2K / 11.1 GB50
Pythia 2.8B2K / 5.7 GB11038033
...thia 2.8B Mitchell Sft Hh Rlhf2K / 11.1 GB140
Pythia 2.8B Sft Hh Rlhf2K / 5.6 GB50
TLDR Pythia2.8B SFT2K / 11.1 GB60
...ythia 2.8B Helpful Sft 3epochs2K / 5.6 GB70
Indication PYT V22K / 5.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than EleutherAI/pythia-2.8b-deduped.

Rank the Pythia 2.8B Deduped 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer