What are the hardware requirements for Pythia 70M Deduped Cleansharegpt En?

Pythia 70M Deduped Cleansharegpt En requires approximately 0.3 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 Cleansharegpt En and how large is it?

Pythia 70M Deduped Cleansharegpt En is developed by HWERI, 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 Cleansharegpt En perform on standard benchmarks?

Pythia 70M Deduped Cleansharegpt En has the following published scores: MMLU 25.24. Compare against reference models on this page or on the LLM Explorer leaderboards.

Pythia 70M Deduped Cleansharegpt En by HWERI — VRAM 0.3GB, 2K context

Name: Pythia 70M Deduped Cleansharegpt En
Author: HWERI

Pythia 70M Deduped Cleansharegpt En is an open-source language model by HWERI. Features: 70m LLM, VRAM: 0.3GB, Context: 2K, License: apache-2.0, LLM Explorer Score: 0.14, Arc: 21.2, HellaSwag: 27.2, MMLU: 25.2.

Dataset:shibing624/sharegpt gp... En Endpoints compatible Gpt neox Pytorch Region:us

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

Pythia 70M Deduped Cleansharegpt En Parameters and Internals

Model Type

text generation

Supported Languages

en (The only supported language for this model is English.)

Training Details

Data Sources:

shibing624/sharegpt_gpt4

Data Volume:

3507 instances

Methodology:

The dataset is cleaned by removing duplicates and paraphrases.

LLM Name	Pythia 70M Deduped Cleansharegpt En
Repository 🤗	https://huggingface.co/HWERI/pythia-70m-deduped-cleansharegpt-en
Model Size	70m
Required VRAM	0.3 GB
Updated	2026-08-08
Maintainer	HWERI
Model Type	gpt_neox
Model Files	0.3 GB
Supported Languages	en
Model Architecture	GPTNeoXForCausalLM
License	apache-2.0
Context Length	2048
Model Max Length	2048
Transformers Version	4.31.0
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50280
Torch Data Type	float32

Rank the Pythia 70M Deduped Cleansharegpt En 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 Cleansharegpt En

Best Alternatives	Context / RAM	Downloads	Likes
Pythia 70M Deduped	2K / 0.2 GB	677080	29
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
...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

Note: green Score (e.g. "73.2") means that the model is better than HWERI/pythia-70m-deduped-cleansharegpt-en.