# OpenMed-NER-PharmaDetect-SuperClinical-434M by OpenMed Source: https://savrn.com/models/openmed-ner-pharmadetect-superclinical-434m Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve OpenMed-NER-PharmaDetect-SuperClinical-434M (434M 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 | 0.9 GB | 1.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.4 GB | 0.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.2 GB | 0.3 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 25, 2026. [OpenMed-NER-PharmaDetect-SuperClinical-434M on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/openmed-ner-pharmadetect-superclinical-434m/gpus) ## SAVRN's Notes on OpenMed-NER-PharmaDetect-SuperClinical-434M This is the largest of OpenMed's chemical and drug recognizers, a 434M-parameter DeBERTa-v2 model trained on BC5CDR, and the most downloaded of the three in our catalog. Apache 2.0 allows commercial use. Use it when accuracy matters more than speed and your documents fit within 512 tokens per pass; otherwise the ModernClinical version reads longer text in one go. SAVRN Research, 2026-09-18 ## Model Card By OpenMed, published under apache-2.0, revision d4259d05b0e9. Specialized model for Chemical Entity Recognition - Chemical entities from the BC5CDR dataset ### Model Overview This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for chemical entity recognition - chemical entities from the bc5cdr dataset. 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. #### Key Features - High Precision: Optimized for biomedical entity recognition - Domain-Specific: Trained on curated BC5CDR_CHEM dataset - Production-Ready: Validated on clinical benchmarks - Easy Integration: Compatible with Hugging Face Transformers ecosystem #### Supported Entity Types This model can identify and classify the following biomedical entities: - B-CHEM - I-CHEM ### Dataset BC5CDR-Chem focuses on chemical entity recognition from the BioCreative V Chemical-Disease Relation extraction task. [Read the full model card (1,067 words)](https://savrn.com/models/openmed-ner-pharmadetect-superclinical-434m/card) ## Configuration Architecture DebertaV2ForTokenClassification Context length (tokens) 512 Layers 24 Hidden size 1,024 Feed-forward size 4,096 Attention heads 16 Vocabulary size 128,100 Stored precision bfloat16 Model type deberta-v2 ## Identity and Version Repository OpenMed/OpenMed-NER-PharmaDetect-SuperClinical-434M Publisher OpenMed Task Token classification Modality Text Library transformers Parameters 434M parameters Languages en Revision d4259d05b0e924ad786f5c342ddedf46fe956331 First published 2025-07-16 Last updated 2025-08-05 ## Files and Weights 11 files, 879.7 MB in total. The weights are 1 file totalling 868.1 MB in safetensors. Weights1 file · 868.1 MB Configuration4 files · 1.5 KB Tokenizer2 files · 8.7 MB Documentation1 file · 11.6 KB Other2 files · 3.0 MB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 868.1 MB | 8c89118f29dc | | added_tokens.json | Configuration | 23 B | — | | config.json | Configuration | 988 B | — | | special_tokens_map.json | Configuration | 286 B | — | | test_results.json | Configuration | 196 B | — | | README.md | Documentation | 11.6 KB | — | | openmed_vs_sota_grouped_bars.png | Other | 497.0 KB | 626b37d9b20c | | spm.model | Other | 2.5 MB | c679fbf93643 | | .gitattributes | Repository | 1.6 KB | — | | tokenizer.json | Tokenizer | 8.7 MB | — | | tokenizer_config.json | Tokenizer | 1.3 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 868.1 MB [Download from OpenMed](https://huggingface.co/OpenMed/OpenMed-NER-PharmaDetect-SuperClinical-434M) Released by OpenMed through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Described by [arXiv:2508.01630](https://savrn.com/papers/openmed-ner-open-source-domain-adapted-state-of-the-art-transformers-for-biomedical-ner-ac) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 868.1 MB | | 16-bit | 0.9 GB | | 8-bit | 0.4 GB | | 4-bit | 0.2 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About OpenMed-NER-PharmaDetect-SuperClinical-434M ### How much GPU memory does OpenMed-NER-PharmaDetect-SuperClinical-434M need? About 1 GB at 16-bit and 0.3 GB at 4-bit: the weights (434M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run OpenMed-NER-PharmaDetect-SuperClinical-434M 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 OpenMed-NER-PharmaDetect-SuperClinical-434M commercially? Yes. OpenMed-NER-PharmaDetect-SuperClinical-434M is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is OpenMed-NER-PharmaDetect-SuperClinical-434M's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Token classification ### [OpenMed-NER-DiseaseDetect-SuperClinical-434M](https://savrn.com/models/openmed-ner-diseasedetect-superclinical-434m) [OpenMed](https://savrn.com/model-publishers/openmed) Specialized model for Disease Entity Recognition - Disease entities from the BC5CDR dataset This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for disease entity recognition - disease entities from the bc5cdr dataset. 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.… Open weights apache-2.0 434M parameters 512 tokens transformers [View model](https://savrn.com/models/openmed-ner-diseasedetect-superclinical-434m) Model · Token classification ### [goby-9-ie-vi](https://savrn.com/models/goby-9-ie-vi) [Belumind](https://savrn.com/model-publishers/belumind) Joint entity + relation extraction for Vietnamese. The best-calibrated model in the goby family: higher precision at the same recall than its siblings. On clean text at each model own best threshold it ties goby-4 rather than beating it (see Measurement correction); on degraded text it is the worst of the family. Pick it for well-formed prose where you care about precision. Fine-tuned from knowledgator/gliner-relex-large-v1.0. Released by Belumind. Apache-2.0. Try it in the browser - no install, runs on ZeroGPU. goby-9 is not robust to degraded text - see Known limitations. That is not a small caveat, read it before choosing. Same training data as goby-4. The only difference is the loss… Open weights apache-2.0 467M parameters gliner [View model](https://savrn.com/models/goby-9-ie-vi) Model · Token classification ### [goby-7-ie-vi](https://savrn.com/models/goby-7-ie-vi) [Belumind](https://savrn.com/model-publishers/belumind) Open weights apache-2.0 467M parameters gliner [View model](https://savrn.com/models/goby-7-ie-vi) Model · Token classification ### [goby-4-ie-vi](https://savrn.com/models/goby-4-ie-vi) [Belumind](https://savrn.com/model-publishers/belumind) Open weights apache-2.0 467M parameters gliner [View model](https://savrn.com/models/goby-4-ie-vi) Model · Token classification ### [OpenMed-NER-ChemicalDetect-ModernMed-395M](https://savrn.com/models/openmed-ner-chemicaldetect-modernmed-395m) [OpenMed](https://savrn.com/model-publishers/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 396M parameters 8,192 tokens transformers [View model](https://savrn.com/models/openmed-ner-chemicaldetect-modernmed-395m) Model · Token classification ### [OpenMed-NER-GenomeDetect-ModernMed-395M](https://savrn.com/models/openmed-ner-genomedetect-modernmed-395m) [OpenMed](https://savrn.com/model-publishers/openmed) Specialized model for Gene/Protein Entity Recognition - Gene and protein mentions This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for gene/protein entity recognition - gene and protein mentions. 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… Open weights apache-2.0 396M parameters 8,192 tokens transformers [View model](https://savrn.com/models/openmed-ner-genomedetect-modernmed-395m) ## OpenMed [All models and datasets](https://savrn.com/model-publishers/openmed) ## Versions - [d4259d05b0e9](https://savrn.com/models/openmed-ner-pharmadetect-superclinical-434m/versions/d4259d05b0e9) · current 2026-09-18 ## Explore More - [All token classification models](https://savrn.com/models/tasks/token-classification) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Hugging Face record](https://huggingface.co/OpenMed/OpenMed-NER-PharmaDetect-SuperClinical-434M) - [How the hub is built](https://savrn.com/model-hub/methodology)