# distilbert-NER by D: Open-Weight Model Source: https://savrn.com/models/distilbert-ner Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve distilbert-NER (65M 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 | 0.1 GB | 0.2 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 | 0.0 GB | 0.0 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 | 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 24, 2026. [distilbert-NER on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/distilbert-ner/gpus) ## SAVRN's Notes on distilbert-NER distilbert-NER is the fast member of the most used English NER family in our catalog. Same author as bert-base-NER, same CoNLL-2003 labels for people, organizations, locations and miscellaneous names, but on DistilBERT at 65M parameters, about 40 percent smaller than the base model. Apache 2.0 allows commercial use. Choose it when you tag high volumes of short text and latency matters more than the last point of accuracy. Like its siblings, it learned from news, so check it on your own domain before you rely on it. SAVRN Research, 2026-09-18 ## Model Card By D, published under apache-2.0, revision dfa2838a1273. If my open source models have been useful to you, please consider supporting me in building small, useful AI models for everyone (and help me afford med school / help out my parents financially). Thanks! ### Model description distilbert-NER is the fine-tuned version of DistilBERT, which is a distilled variant of the BERT model. DistilBERT has fewer parameters than BERT, making it smaller, faster, and more efficient. distilbert-NER is specifically fine-tuned for the task of Named Entity Recognition (NER). This model accurately identifies the same four types of entities as its BERT counterparts: location (LOC), organizations (ORG), person (PER), and Miscellaneous (MISC). Although it is a more compact model, distilbert-NER demonstrates a robust performance in NER tasks, balancing between size, speed, and accuracy. The model was fine-tuned on the English version of the [CoNLL-2003 Named Entity Recognition](https://www.aclweb.org/anthology/W03-0419.pdf) dataset, which is widely recognized for its comprehensive and diverse range of entity types. #### Available NER models [Read the full model card (689 words)](https://savrn.com/models/distilbert-ner/card) ## Configuration Architecture DistilBertForTokenClassification Context length (tokens) 512 Vocabulary size 28,996 Stored precision float32 Model type distilbert ## Identity and Version Repository dslim/distilbert-NER Publisher D Task Token classification Modality Text Library transformers Parameters 65M parameters Languages en Revision dfa2838a127384aabb82ed7719e16dab84c42a2a First published 2024-01-25 Last updated 2024-10-08 ## Files and Weights 17 files, 523.5 MB in total. The weights are 3 files totalling 521.7 MB in bin, onnx, safetensors. Weights3 files · 521.7 MB Configuration4 files · 2.7 KB Tokenizer6 files · 1.8 MB Documentation1 file · 6.2 KB Other2 files · 7.6 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 260.8 MB | 235ecd699f65 | | onnx/model.onnx | Weights | 260.9 MB | 4440f9fc64cd | | training_args.bin | Weights | 4.5 KB | 2fea728bc126 | | config.json | Configuration | 926 B | — | | onnx/config.json | Configuration | 925 B | — | | onnx/special_tokens_map.json | Configuration | 695 B | — | | special_tokens_map.json | Configuration | 125 B | — | | README.md | Documentation | 6.2 KB | — | | runs/Jan25_20-44-33_2320f22f76d4/events.out.tfevents.1706215489.2320f22f76d4.240.0 | Other | 7.0 KB | 2c1042dee9e6 | | runs/Jan25_20-44-33_2320f22f76d4/events.out.tfevents.1706216274.2320f22f76d4.240.1 | Other | 560 B | 7cfcd444853c | | .gitattributes | Repository | 1.5 KB | — | | onnx/tokenizer.json | Tokenizer | 669.0 KB | — | | onnx/tokenizer_config.json | Tokenizer | 1.3 KB | — | | onnx/vocab.txt | Tokenizer | 213.4 KB | — | | tokenizer.json | Tokenizer | 669.0 KB | — | | tokenizer_config.json | Tokenizer | 1.2 KB | — | | vocab.txt | Tokenizer | 213.4 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 521.7 MB [Download from D](https://huggingface.co/dslim/distilbert-NER) Released by D through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from distilbert/distilbert-base-cased - Described by [arXiv:1810.04805](https://savrn.com/papers/bert-pre-training-of-deep-bidirectional-transformers-for-language-understanding) - Described by [arXiv:1910.01108](https://savrn.com/papers/distilbert-a-distilled-version-of-bert-smaller-faster-cheaper-and-lighter) - Quantized from distilbert/distilbert-base-cased - Trained on (disclosed) conll2003 ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 521.7 MB | | 16-bit | 0.1 GB | | 8-bit | 0.1 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About distilbert-NER ### How much GPU memory does distilbert-NER need? About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (65M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run distilbert-NER 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 distilbert-NER commercially? Yes. distilbert-NER 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 distilbert-NER's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Token classification ### [OpenMed-NER-BloodCancerDetect-TinyMed-65M](https://savrn.com/models/openmed-ner-bloodcancerdetect-tinymed-65m) [OpenMed](https://savrn.com/model-publishers/openmed) Specialized model for Clinical Entity Recognition - Clinical entities related to Chronic Lymphocytic Leukemia This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for clinical entity recognition - clinical entities related to chronic lymphocytic leukemia. 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… Open weights apache-2.0 65M parameters 512 tokens transformers [View model](https://savrn.com/models/openmed-ner-bloodcancerdetect-tinymed-65m) Model · Token classification ### [biomedical-ner-all](https://savrn.com/models/biomedical-ner-all) [D 4 Data Community](https://savrn.com/model-publishers/d4data) An English Named Entity Recognition model, trained on Maccrobat to recognize the bio-medical entities (107 entities) from a given text corpus (case reports etc.). This model was built on top of distilbert-base-uncased Checkout the tutorial video for explanation of this model and corresponding python library: https://youtu.be/xpiDPdBpS18 The easiest way is to load the inference api from huggingface and second method is through the pipeline object offered by transformers library. This model is part of the Research topic "AI in Biomedical field" conducted by Deepak John Reji, Shaina Raza. If you use this work (code, model or dataset), please star at Open weights apache-2.0 66M parameters 512 tokens transformers [View model](https://savrn.com/models/biomedical-ner-all) Model · Token classification ### [OpenMed-NER-OrganismDetect-TinyMed-82M](https://savrn.com/models/openmed-ner-organismdetect-tinymed-82m) [OpenMed](https://savrn.com/model-publishers/openmed) Specialized model for Species Entity Recognition - Species names from the Species-800 dataset This model is a state-of-the-art fine-tuned transformer engineered to deliver enterprise-grade accuracy for species entity recognition - species names from the species-800 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… Open weights apache-2.0 82M parameters 514 tokens transformers [View model](https://savrn.com/models/openmed-ner-organismdetect-tinymed-82m) Model · Token classification ### [zh-pii-tagger-35m](https://savrn.com/models/zh-pii-tagger-35m) [Chao Ma](https://savrn.com/model-publishers/ickma2311) A 35M-parameter token tagger for personal data in Chinese and mixed Chinese–English text. It is a fine-tune of cjhwong/seatbelt-pii-tagger with the same architecture, tokenizer and 18 types / 73 BIOES labels. - real Chinese contexts (FineWeb-2) with inserted synthetic private names and addresses; - self-distillation replay, which aims to reduce forgetting of the base model's other types and its English behaviour. - It misses fewer Chinese person names. On test sets never used during development, person recall rises by about 2 to 10 points; precision moves between −3.5 and +3.5 points. - +0.6 to +2.1 on two freshly generated test sets; - +4.2 to +6.7 on an MSRA NER train sample (never used… Open weights apache-2.0 35M parameters 512 tokens [View model](https://savrn.com/models/zh-pii-tagger-35m) Model · Token classification ### [physics-ai999x](https://savrn.com/models/physics-ai999x) [AI999X Labs](https://savrn.com/model-publishers/ai999x) License: Apache-2.0 · Author: Ibnul Jaif Farabi (creator and engineer) · Organization: AI999X · Version 2.0.0 physics-ai999x is an offline, deterministic Python solver that answers physics questions with verified results from 148 certified capabilities, gives 859 documented answers identically on Windows and Linux, and refuses rather than guesses when an answer cannot be verified. physics-ai999x is a compact, deterministic physics engine for Python. It reads a question in plain English (or a typed call), picks a certified physics capability, computes the answer exactly, checks it, and returns the result with its steps, units, LaTeX and assumptions — or an honest refusal that says what is… Open weights apache-2.0 34M parameters physics-ai999x [View model](https://savrn.com/models/physics-ai999x) Model · Token classification ### [algebra-ai999x](https://savrn.com/models/algebra-ai999x) [AI999X Labs](https://savrn.com/model-publishers/ai999x) License: Apache-2.0 · Author: Ibnul Jaif Farabi (creator and engineer) · Organization: AI999X · Version 2.0.0 algebra-ai999x is an offline, deterministic Python solver that answers algebra questions with verified results from 56 certified capabilities, gives 230 documented answers identically on Windows and Linux, and refuses rather than guesses when an answer cannot be verified. algebra-ai999x is a compact, deterministic algebra engine for Python. It reads a question in plain English (or a typed call), picks a certified algebra capability, computes the answer exactly, checks it, and returns the result with its steps, units, LaTeX and assumptions — or an honest refusal that says what is… Open weights apache-2.0 33M parameters algebra-ai999x [View model](https://savrn.com/models/algebra-ai999x) ## D [All models and datasets](https://savrn.com/model-publishers/dslim) ## Versions - [dfa2838a1273](https://savrn.com/models/distilbert-ner/versions/dfa2838a1273) · 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/dslim/distilbert-NER) - [How the hub is built](https://savrn.com/model-hub/methodology)