2026-10-13-xlmr-large-baseline_2_3 by Clara Wan Ching Ho

Runs On

What it takes to serve 2026-10-13-xlmr-large-baseline_2_3 (559M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

Precision	Weights	Memory needed	Cheapest setup	Per hour	Also fits
16-bit	1.1 GB	1.3 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	0.6 GB	0.7 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	0.3 GB	0.3 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 24, 2026.

2026-10-13-xlmr-large-baseline_2_3 on every accelerator the SAVRN Index prices, at every precision

Model Card

By Clara Wan Ching Ho, published under mit, revision 2069ef47bd79.

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 3e-05 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 8 - totaltrainbatchsize: 64 - lrschedulertype: linear - lrschedulerwarmupratio: 0.1 - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 4.57.6 - Pytorch 2.5.1+cu121 - Datasets 3.2.0 - Tokenizers 0.22.2

Read Clara Wan Ching Ho's full model card

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3091 - Precision: 0.5717 - Recall: 0.4948 - F1: 0.5305 - Accuracy: 0.9512 - Academicdiscipline F1: 0.3478 - Ambiguouslydefinedconcept F1: 0.0580 - Discoursephenomenon F1: 0.2143 - Graphemicphenomenon F1: 0.1429 - Languagerelatedterm F1: 0.7249 - Languageresourceinformation F1: 0.3117 - Lexicalphenomenon F1: 0.4426 - Morphologicalphenomenon F1: 0.5714 - Morphosyntacticphenomenon F1: 0.7315 - New Tag F1: 0.4504 - Otherlinguisticterm F1: 0.5151 - Phonologicalphenomenon F1: 0.6934 - Semanticphenomenon F1: 0.1593 - Syntacticphenomenon F1: 0.6200 - Topnode Dummy F1: 0.3231 - Unclassifiedlinguisticconcept F1: 0.3846

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 64 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 - mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Academicdiscipline F1	Ambiguouslydefinedconcept F1	Discoursephenomenon F1	Graphemicphenomenon F1	Languagerelatedterm F1	Languageresourceinformation F1	Lexicalphenomenon F1	Morphologicalphenomenon F1	Morphosyntacticphenomenon F1	New Tag F1	Otherlinguisticterm F1	Phonologicalphenomenon F1	Semanticphenomenon F1	Syntacticphenomenon F1	Topnode Dummy F1	Unclassifiedlinguisticconcept F1
No log	1.0	260	0.2062	0.4511	0.2930	0.3553	0.9408	0.0	0.0	0.0	0.0	0.6015	0.0863	0.0	0.2967	0.6220	0.0863	0.3193	0.4864	0.0	0.3738	0.1801	0.0
0.4931	2.0	520	0.2048	0.4270	0.5307	0.4732	0.9389	0.0	0.0	0.0	0.0	0.6630	0.5594	0.3151	0.4177	0.6398	0.3799	0.3605	0.5954	0.1046	0.4790	0.3887	0.2532
0.4931	3.0	780	0.2081	0.5163	0.4562	0.4844	0.9472	0.0	0.0	0.0	0.0	0.7022	0.3218	0.3904	0.4352	0.6872	0.3253	0.4677	0.5957	0.1039	0.5578	0.2116	0.5556
0.0849	4.0	1040	0.2054	0.5159	0.4881	0.5016	0.9471	0.3	0.0	0.0	0.0	0.6651	0.2624	0.4471	0.5852	0.7154	0.3851	0.4775	0.6090	0.1389	0.6102	0.3387	0.4255
0.0849	5.0	1300	0.2171	0.5528	0.4892	0.5190	0.9496	0.1905	0.0851	0.0	0.0	0.7053	0.2423	0.5032	0.5776	0.7148	0.4017	0.4826	0.6616	0.1363	0.6004	0.3249	0.3846
0.0427	6.0	1560	0.2467	0.5270	0.4755	0.4999	0.9481	0.1905	0.0615	0.0	0.0	0.6806	0.2846	0.4453	0.5848	0.7314	0.3794	0.4874	0.6112	0.1322	0.5905	0.3027	0.3077
0.0427	7.0	1820	0.2673	0.5404	0.4904	0.5142	0.9489	0.2105	0.0299	0.0	0.1290	0.7123	0.3168	0.4264	0.5363	0.7167	0.3901	0.5030	0.6746	0.1449	0.6030	0.3039	0.4545
0.0224	8.0	2080	0.2769	0.5471	0.5002	0.5226	0.9497	0.2105	0.1556	0.2667	0.125	0.7112	0.3339	0.4575	0.5080	0.7268	0.4487	0.5051	0.6742	0.1543	0.6191	0.3130	0.4082
0.0224	9.0	2340	0.3020	0.5638	0.4882	0.5233	0.9508	0.4	0.0	0.2143	0.1379	0.7236	0.3051	0.4390	0.5993	0.7353	0.4111	0.4949	0.6856	0.1570	0.6091	0.3076	0.3922
0.0121	10.0	2600	0.3091	0.5717	0.4948	0.5305	0.9512	0.3478	0.0580	0.2143	0.1429	0.7249	0.3117	0.4426	0.5714	0.7315	0.4504	0.5151	0.6934	0.1593	0.6200	0.3231	0.3846

Framework versions

Transformers 4.57.6
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.22.2

Configuration

Architecture: XLMRobertaForTokenClassification
Context length (tokens): 514
Layers: 24
Hidden size: 1,024
Feed-forward size: 4,096
Attention heads: 16
Vocabulary size: 250,002
Model type: xlm-roberta

Identity and Version

Repository: c-ho/2026-10-13-xlmr-large-baseline_2_3
Publisher: Clara Wan Ching Ho
Task: Token classification
Modality: Text
Library: transformers
Parameters: 559M parameters
Languages: xlm-roberta
Revision: 2069ef47bd79e4a80c3855fd53f37036b793f18d
First published: 2026-10-13
Last updated: 2026-10-13

Files and Weights

9 files, 2.3 GB in total. The weights are 2 files totalling 2.2 GB in bin, safetensors.

Weights2 files · 2.2 GB

Configuration2 files · 3.2 KB

Tokenizer2 files · 17.1 MB

Documentation1 file · 8.2 KB

Other1 file · 5.1 MB

Repository1 file · 1.6 KB

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	2.2 GB	1daa7f2537a0
training_args.bin	Weights	5.5 KB	6b12b97e9a98
config.json	Configuration	3.0 KB	—
special_tokens_map.json	Configuration	280 B	—
README.md	Documentation	8.2 KB	—
sentencepiece.bpe.model	Other	5.1 MB	cfc8146abe2a
.gitattributes	Repository	1.6 KB	—
tokenizer.json	Tokenizer	17.1 MB	883b03711108
tokenizer_config.json	Tokenizer	1.2 KB	—

License and Download

License: mit
Access: Open weights, no gate
Download size: 2.2 GB

Download from Clara Wan Ching Ho

Released by Clara Wan Ching Ho through its official repository on Hugging Face. Read the license.

Built From

Derived from FacebookAI/xlm-roberta-large

Memory Requirements

Precision	Weights in memory
As published	2.2 GB
16-bit	1.1 GB
8-bit	0.6 GB
4-bit	0.3 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About 2026-10-13-xlmr-large-baseline_2_3

How much GPU memory does 2026-10-13-xlmr-large-baseline_2_3 need?

About 1.3 GB at 16-bit and 0.3 GB at 4-bit: the weights (559M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run 2026-10-13-xlmr-large-baseline_2_3 on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use 2026-10-13-xlmr-large-baseline_2_3 commercially?

Yes. 2026-10-13-xlmr-large-baseline_2_3 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

What is 2026-10-13-xlmr-large-baseline_2_3's context length?

514 tokens, from the maximum position embeddings in its published configuration.

Similar Models

Model · Token classification

2026-10-13-xlmr-large-baseline_2_4

Clara Wan Ching Ho

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 8 - totaltrainbatchsize: 64 - lrschedulertype: linear - lrschedulerwarmupratio: 0.1 - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 4.57.6 - Pytorch 2.5.1+cu121 - Datasets 3.2.0 - Tokenizers 0.22.2

Open weights mit 559M parameters 514 tokens transformers

View model

Model · Token classification

2026-10-13-xlmr-large-baseline_2_2

Clara Wan Ching Ho

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 8 - evalbatchsize: 8 - gradientaccumulationsteps: 8 - totaltrainbatchsize: 64 - lrschedulertype: linear - lrschedulerwarmupratio: 0.1 - numepochs: 10 - mixedprecisiontraining: Native AMP - Transformers 4.57.6 - Pytorch 2.5.1+cu121 - Datasets 3.2.0 - Tokenizers 0.22.2

Open weights mit 559M parameters 514 tokens transformers

View model

Model · Token classification

chitragupta-pii-indic

Arun Prabhakaran

Open weights apache-2.0 559M parameters transformers

View model

Model · Token classification

fullstop-punctuation-multilang-large

Oliver Guhr

This model predicts the punctuation of English, Italian, French and German texts. We developed it to restore the punctuation of transcribed spoken language. This multilanguage model was trained on the Europarl Dataset provided by the SEPP-NLG Shared Task. Please note that this dataset consists of political speeches. Therefore the model might perform differently on texts from other domains. The model restores the following punctuation markers: "." "," "?" "-" ":" We provide a simple python package that allows you to process text of any length. To get started install the package from pypi: output output The performance differs for the single punctuation markers as hyphens and colons, in many…

Open weights mit 559M parameters 514 tokens transformers

View model

Model · Token classification

OpenMed-NER-GenomicDetect-BigMed-560M

OpenMed

Specialized model for Gene Entity Recognition - Gene-related entities This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for gene entity recognition - gene-related entities. This specialized model excels at identifying and extracting biomedical entities from clinical texts, research papers, and healthcare documents, enabling applications such as drug interaction detection, medication extraction from patient records, adverse event monitoring, literature mining for drug discovery, and biomedical knowledge graph construction with production-ready reliability for clinical and research applications. This model can identify and classify the…

Open weights apache-2.0 559M parameters 514 tokens transformers

View model

Model · Token classification

OpenMed-NER-ChemicalDetect-BigMed-560M

OpenMed

Specialized model for Chemical Entity Recognition - Identifies chemical compounds and substances in biomedical literature This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for chemical entity recognition - identifies chemical compounds and substances in biomedical literature. This specialized model excels at identifying and extracting biomedical entities from clinical texts, research papers, and healthcare documents, enabling applications such as drug interaction detection, medication extraction from patient records, adverse event monitoring, literature mining for drug discovery, and biomedical knowledge graph construction with…

Open weights apache-2.0 559M parameters 514 tokens transformers

View model