What are the hardware requirements for Pythia 160M C2s?

Pythia 160M C2s requires approximately 0.6 GB of VRAM and supports a context window of 8K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Pythia 160M C2s and how large is it?

Pythia 160M C2s is developed by vandijklab, a model with 160m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Pythia 160M C2s?

Pythia 160M C2s is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Pythia 160M C2s by vandijklab — VRAM 0.6GB, 8K context

Name: Pythia 160M C2s
Author: vandijklab

Pythia 160M C2s is an open-source language model by vandijklab. Features: 160m LLM, VRAM: 0.6GB, Context: 8K, License: cc-by-4.0, LLM Explorer Score: 0.11.

Arxiv:2304.01373 Dataset:vandijklab/immune-c2s Deploy:azure En Endpoints compatible Gpt neox Pytorch Region:us Safetensors Scrna-seq

Model Card on HF 🤗: https://huggingface.co/vandijklab/pythia-160m-c2s

Pythia 160M C2s Parameters and Internals

Model Type

causal-lm

Use Cases

Areas:

Research, Single-cell transcriptomics

Applications:

Single-cell RNA sequencing analyses, Cell type prediction

Primary Use Cases:

Conditional cell generation, Unconditional cell generation

Considerations:

Best used with adequate hardware for full cell generation.

Additional Notes

Cell2Sentence provides a novel approach for single-cell RNA sequencing data analysis by transforming it into cell sentences.

Supported Languages

en (proficient)

Training Details

Data Sources:

immune tissue dataset from Domínguez et al.

Methodology:

Cell2Sentence method for adapting large language models to single-cell transcriptomics.

Training Time:

20 hours

Hardware Used:

8 A100 40GB GPUs

Model Architecture:

Transform single-cell RNA sequencing data into sequences of gene names ordered by expression level, termed "cell sentences".

Input Output

Input Format:

Gene names ordered by expression level

Accepted Modalities:

text

Output Format:

Cell sentences with gene expressions

Performance Tips:

Use an A100 GPU for better inference speed and memory capacity.

LLM Name	Pythia 160M C2s
Repository 🤗	https://huggingface.co/vandijklab/pythia-160m-c2s
Model Size	160m
Required VRAM	0.6 GB
Updated	2026-07-20
Maintainer	vandijklab
Model Type	gpt_neox
Model Files	0.6 GB
Supported Languages	en
Model Architecture	GPTNeoXForCausalLM
License	cc-by-4.0
Context Length	9200
Model Max Length	9200
Transformers Version	4.37.1
Tokenizer Class	GPTNeoXTokenizer
Vocabulary Size	50304
Torch Data Type	float32

Rank the Pythia 160M C2s 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 160M C2s

Best Alternatives	Context / RAM	Downloads	Likes
Violet 160M Chat	4K / 0.3 GB	13	0
Pythia 160M	2K / 0.4 GB	2294174	44
Pythia 160M Deduped	2K / 0.4 GB	133437	3
Pythia 160M Xsum Roya	2K / 0.6 GB	6	0
Pythia 160m Sft	2K / 0 GB	8	0
Sheared Pythia 160M	2K / 0.7 GB	53	4
Pythia160m Sft Tldr	2K / 0.6 GB	175	0
Pythia 160M Dolphin Extended	2K / 0.3 GB	93	0
Pythia 160M Storytelling	2K / 0.3 GB	7	0
...hia 160M Deduped Step92k 193bt	2K / 0.4 GB	120	0

Note: green Score (e.g. "73.2") means that the model is better than vandijklab/pythia-160m-c2s.