What are the hardware requirements for Pythia 70M Deduped?

Pythia 70M Deduped requires approximately 0.2 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Pythia 70M Deduped and how large is it?

Pythia 70M Deduped is developed by EleutherAI, a model with 70m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Pythia 70M Deduped perform on standard benchmarks?

Pythia 70M Deduped has the following published scores: MMLU 25.26. Compare against reference models on this page or on the LLM Explorer leaderboards.

Pythia 70M Deduped by EleutherAI — VRAM 0.2GB, 2K context

Name: Pythia 70M Deduped
Author: EleutherAI

Pythia 70M Deduped is an open-source language model by EleutherAI. Features: 70m LLM, VRAM: 0.2GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.19, Arc: 21.1, HellaSwag: 27.2, MMLU: 25.3.

Arxiv:2101.00027 Arxiv:2201.07311 Arxiv:2304.01373 Dataset:eleutherai/the pile de... Deploy:sagemaker En Endpoints compatible Gpt neox Pythia Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/EleutherAI/pythia-70m-deduped

Pythia 70M 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 Name	Pythia 70M Deduped
Repository 🤗	https://huggingface.co/EleutherAI/pythia-70m-deduped
Model Size	70m
Required VRAM	0.2 GB
Updated	2026-07-30
Maintainer	EleutherAI
Model Type	gpt_neox
Model Files	0.2 GB 0.2 GB
Supported Languages	en
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.24.0
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50304
Torch Data Type	float16

Rank the Pythia 70M Deduped capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to Pythia 70M Deduped

Best Alternatives	Context / RAM	Downloads	Likes
Pythia 70M	2K / 0.2 GB	519616	85
Pythia 70m Sft Hh	2K / 0.1 GB	9	0
Pythia 70M Multi	2K / 0.3 GB	6	0
Pythia Chinese 70M UDN	2K / 0.2 GB	18	0
Pythia 70m Sft	2K / 0.3 GB	7	0
...ythia 70M Wikipedia Paragraphs	2K / 0.3 GB	4	3
...a 70M Deduped Cleansharegpt En	2K / 0.3 GB	52	0
...thia 70M Deduped Cleansharegpt	2K / 0.3 GB	138	1
Chessdevilai	2K / 0.3 GB	5	0
...ythia 70M Deduped Step44k 92bt	2K / 0.2 GB	113	0