What are the hardware requirements for Coref Bert Large?

Coref Bert Large requires approximately 1.3 GB of VRAM and supports a context window of 0.5K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Coref Bert Large and how large is it?

Coref Bert Large is developed by nielsr, a model with 334.7m 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 Coref Bert Large?

Coref Bert Large is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Coref Bert Large by nielsr — VRAM 1.3GB, 0.5K context

Name: Coref Bert Large
Author: nielsr

Coref Bert Large is an open-source language model by nielsr. Features: 334.7m LLM, VRAM: 1.3GB, Context: 0.5K, License: apache-2.0, LLM Explorer Score: 0.

Arxiv:2004.06870 Dataset:docred Dataset:fever Dataset:gap Dataset:nyu-mll/glue Dataset:quoref Dataset:wikipedia Dataset:winogender Dataset:winograd wsc En Endpoints compatible Exbert Pytorch Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/nielsr/coref-bert-large

Coref Bert Large Parameters and Internals

Model Type

Masked Language Modeling (MLM), Mention Reference Prediction (MRP)

Additional Notes

The CorefBERT model is pretrained in a self-supervised fashion allowing it to be trained on large publicly available datasets without labeled data.

Supported Languages

English (Proficient)

Training Details

Data Sources:

wikipedia, quoref, docred, fever, gap, winograd_wsc, winogender, nyu-mll/glue

Model Architecture:

Transformers

LLM Name	Coref Bert Large
Repository 🤗	https://huggingface.co/nielsr/coref-bert-large
Model Size	334.7m
Required VRAM	1.3 GB
Updated	2026-07-15
Maintainer	nielsr
Model Files	1.3 GB 1.3 GB
Supported Languages	en
Model Architecture	AutoModel
License	apache-2.0
Context Length	512
Model Max Length	512
Vocabulary Size	28996

Rank the Coref Bert Large 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