# bionerd-re by Joshy Alphonse: Open-Weight Model Source: https://savrn.com/models/bionerd-re Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve bionerd-re (109M 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 | 0.2 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 | | 8-bit | 0.1 GB | 0.1 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 | 0.1 GB | 0.1 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 9, 2026. [bionerd-re on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/bionerd-re/gpus) ## Model Card By Joshy Alphonse, published under mit, revision 94503c5b79f7. BioNERD's own typed relation-extraction model "C": microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext (MIT) fine-tuned on the BioRED Train split (public domain) as an entity-marker sequence classifier. No accuracy is claimed here. BioNERD shows its measured labels in the app's model catalog, each tied to this exact artefact. Read Joshy Alphonse's full model card ### bionerd-re — C (BiomedBERT, BioRED typed relations) BioNERD's own typed relation-extraction model "C": microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext (MIT) fine-tuned on the BioRED Train split (public domain) as an entity-marker sequence classifier. - Input: text with [E1] … [/E1] and [E2] … [/E2] around the two arguments (the four marker tokens are in the tokenizer). - Labels: 0 = None, then BioRED's eight types in this order: Association, Positive_Correlation, Negative_Correlation, Bind, Cotreatment, Comparison, Drug_Interaction, Conversion. - Training: seed 13, lr 2e-5, batch 16, up to 5 epochs, max length 512, 2 negatives per positive; the best epoch on BioRED Dev typed F1 was kept. No accuracy is claimed here. BioNERD shows its measured labels in the app's model catalog, each tied to this exact artefact. | File | sha256 | | --- | --- | | config.json | 6ac24d941178b632550aa2cb2c81594b9c88463bea01c32c5712064afbb23732 | | model.safetensors | 7a96681585571fa82910d3e547bd71ff83eb5285c0859a37ae272116bbcca598 | | tokenizer_config.json | 8b1605c818426817b2b46a1dbf23e834c7fc893a1a04cbda394382d719cb553a | | tokenizer.json | 8c801ddf1fd1e9591578b90b7e3fa2bc895d80af941ae967f1f1869ea75aaca4 | ## Configuration Architecture BertForSequenceClassification Context length (tokens) 512 Layers 12 Hidden size 768 Feed-forward size 3,072 Attention heads 12 Vocabulary size 30,526 Model type bert ## Identity and Version Repository joshyalphonse/bionerd-re Publisher Joshy Alphonse Task Text classification Modality Text Library transformers Parameters 109M parameters Languages Not stated by the source Revision 94503c5b79f76ae2e5115a1c76d1a116489494a6 First published 2026-10-04 Last updated 2026-10-09 ## Files and Weights 30 files, 1.6 GB in total. The weights are 5 files totalling 1.6 GB in gguf, safetensors. Weights5 files · 1.6 GB Configuration10 files · 27.4 KB Tokenizer7 files · 1.9 MB Documentation7 files · 24.7 KB Repository1 file · 1.7 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | bioredirect/bioredirect.safetensors | Weights | 440.7 MB | 2c233a318c8c | | biorex/model.safetensors | Weights | 433.2 MB | 64526a02797f | | lora-qwen3-8b/qwen3-8b-re-lora.gguf | Weights | 87.3 MB | 7842b213330b | | lora-qwen36-27b/qwen3.6-27b-re-lora.gguf | Weights | 216.2 MB | 299cd7ec7711 | | model.safetensors | Weights | 438.0 MB | 7a9668158557 | | bioredirect/added_tokens.json | Configuration | 1.4 KB | — | | bioredirect/bioredirect.json | Configuration | 604 B | — | | bioredirect/config.json | Configuration | 3.0 KB | — | | bioredirect/special_tokens_map.json | Configuration | 8.0 KB | — | | biorex/added_tokens.json | Configuration | 1.0 KB | — | | biorex/config.json | Configuration | 3.0 KB | — | | biorex/special_tokens_map.json | Configuration | 920 B | — | | config.json | Configuration | 1.1 KB | — | | lora-qwen3-8b/manifest.json | Configuration | 3.0 KB | — | | lora-qwen36-27b/manifest.json | Configuration | 5.3 KB | — | | README.md | Documentation | 1.5 KB | — | | bioredirect/LICENSE-BioLinkBERT-Apache-2.0.txt | Documentation | 11.4 KB | — | | bioredirect/NOTICE.md | Documentation | 2.8 KB | — | | biorex/LICENSE-BiomedBERT-MIT.txt | Documentation | 1.1 KB | — | | biorex/NOTICE.md | Documentation | 3.8 KB | — | | lora-qwen3-8b/README.md | Documentation | 1.6 KB | — | | lora-qwen36-27b/README.md | Documentation | 2.5 KB | — | | .gitattributes | Repository | 1.7 KB | — | | bioredirect/tokenizer_config.json | Tokenizer | 11.2 KB | — | | bioredirect/vocab.txt | Tokenizer | 254.0 KB | — | | biorex/tokenizer.json | Tokenizer | 686.5 KB | — | | biorex/tokenizer_config.json | Tokenizer | 1.2 KB | — | | biorex/vocab.txt | Tokenizer | 254.0 KB | — | | tokenizer.json | Tokenizer | 707.0 KB | — | | tokenizer_config.json | Tokenizer | 460 B | — | ## License and Download License mit Access Open weights, no gate Download size 1.6 GB [Download from Joshy Alphonse](https://huggingface.co/joshyalphonse/bionerd-re) Released by Joshy Alphonse through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Derived from [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://savrn.com/models/biomednlp-biomedbert-base-uncased-abstract-fulltext) - Quantized from [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://savrn.com/models/biomednlp-biomedbert-base-uncased-abstract-fulltext) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 1.6 GB | | 16-bit | 0.2 GB | | 8-bit | 0.1 GB | | 4-bit | 0.1 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About bionerd-re ### How much GPU memory does bionerd-re need? About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (109M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run bionerd-re 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 bionerd-re commercially? Yes. bionerd-re 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 bionerd-re's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Text classification ### [topic-classification-bert](https://savrn.com/models/topic-classification-bert) [KC](https://savrn.com/model-publishers/karencardiel) This model was fine-tuned on the AG News dataset (fancyzhx/agnews) for four-class news topic classification: The dataset was divided into 108,000 training examples, 12,000 validation examples, and 7,600 test examples. A random seed of 42 was used. This model is intended for English news topic classification into the four AG News categories: World, Sports, Business, and Sci/Tech. It was developed for educational purposes and experimentation with BERT adaptation methods. The model is trained on English news data and may not generalize well to other domains or languages. It only supports the four categories present in AG News. Performance on real-world data may differ from the reported… Open weights 109M parameters 512 tokens transformers [View model](https://savrn.com/models/topic-classification-bert) Model · Text classification ### [bert-base-agnews-topic-classification](https://savrn.com/models/bert-base-agnews-topic-classification) [Dalila Ku](https://savrn.com/model-publishers/dalila-ku) Full fine-tuning of bert-base-uncased for 4-class news topic classification, delivered as part of assignment U2T01 (Adapting BERT for NLP tasks — Trends in Data Science, Unit 2, Universidad Politécnica de Yucatán). bert-base-uncased with a linear classification head on top of the [CLS] token's last hidden state, mapping to 4 topic classes: World, Sports, Business, Sci/Tech. - 10% of the official train split was held out as validation; the official test split was left untouched. - 4 balanced classes. Two adaptation methods were trained and compared; full fine-tuning is the delivered model, since it beat the feature-based baseline by a margin well above the run-to-run noise floor (±1–3 points… Open weights apache-2.0 109M parameters 512 tokens [View model](https://savrn.com/models/bert-base-agnews-topic-classification) Model · Text classification ### [ft-agnews](https://savrn.com/models/ft-agnews) [Dalila Ku](https://savrn.com/model-publishers/dalila-ku) This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 32 - evalbatchsize: 64 - lrschedulertype: linear - numepochs: 2 - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 4.8.5 - Tokenizers 0.23.1 Open weights apache-2.0 109M parameters 512 tokens transformers [View model](https://savrn.com/models/ft-agnews) Model · Text classification ### [multi-domain-sentiment-bert](https://savrn.com/models/multi-domain-sentiment-bert) [ADITYA GUPTA](https://savrn.com/model-publishers/adityagupta-data) This is the model card of a transformers model that has been pushed on the Hub. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Use the code below to get started with the model. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). Open weights 109M parameters 512 tokens transformers [View model](https://savrn.com/models/multi-domain-sentiment-bert) Model · Text classification ### [assign5autotrain](https://savrn.com/models/assign5autotrain) [Harsha B Setty](https://savrn.com/model-publishers/harshab1983) libraryname: transformers - autotrain - text-classification basemodel: google-bert/bert-base-uncased f1macro: 0.7533020080884588 f1micro: 0.7533333333333333 f1weighted: 0.7533020080884587 precisionmacro: 0.7551310982162045 precisionmicro: 0.7533333333333333 precisionweighted: 0.7551310982162046 recallmacro: 0.7533333333333333 recallmicro: 0.7533333333333333 recallweighted: 0.7533333333333333 Open weights 109M parameters 512 tokens transformers [View model](https://savrn.com/models/assign5autotrain) Model · Text classification ### [bert-log-anomaly-detection](https://savrn.com/models/bert-log-anomaly-detection) [Aungruk Vanichanai](https://savrn.com/model-publishers/aungmoonlord) 1. bert-log-anomaly-detection is a BERT-based NLP model fine-tuned for single SQL transaction log anomaly detection. 2. The model classifies each database transaction log as either Normal or Anomaly, with the goal of supporting AI-powered fraud detection and cybersecurity monitoring systems. 3. This model was developed as part of the Samsung × KBTG Digital Fraud Cybersecurity Hackathon (Thailand) under the AI-Powered Fraud Detection & Prevention track. This model analyzes individual SQL database transaction logs and detects abnormal patterns that may indicate fraudulent, malicious, or suspicious behavior. - Developed by Waris Sripatoomrak, this model integrates with an n8n workflow to… Open weights apache-2.0 109M parameters 512 tokens transformers [View model](https://savrn.com/models/bert-log-anomaly-detection) ## Joshy Alphonse [All models and datasets](https://savrn.com/model-publishers/joshyalphonse) ## Versions - [94503c5b79f7](https://savrn.com/models/bionerd-re/versions/94503c5b79f7) · current 2026-10-09 - [7ea55694aa4d](https://savrn.com/models/bionerd-re/versions/7ea55694aa4d) 2026-10-07 ## Explore More - [All text classification models](https://savrn.com/models/tasks/text-classification) - [All models under mit](https://savrn.com/models/licenses/mit) - [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 2026-10-09. - [Hugging Face record](https://huggingface.co/joshyalphonse/bionerd-re) - [How the hub is built](https://savrn.com/model-hub/methodology)