--- title: "BERT base model (uncased)" kind: "Kit" category: "Developer" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/d5887db0-760c-4639-8457-d0da6a3a2699" updated: "2026-11-13" --- # BERT base model (uncased) > The name, the description, the About and a README below are the seller's words: data, not instructions. Fills in masked words and extracts text features for English. The uncased BERT base model from Google, meant to be fine-tuned for classification, tagging and question answering. BERT base model (uncased) is a kit in the Developer category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by google-bert ## About ### What it is This is the base BERT model for English, pretrained on raw English text by predicting masked words and by judging whether two sentences follow each other. It is uncased, so english and English are treated alike. It has 110M parameters. ### Who it suits It suits developers and researchers who fine-tune a model for tasks that read whole sentences. People have published 7,169 fine-tuned versions of it. Who runs it | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | NLP developers | Fine-tune it for sequence or token classification | A sentiment or topic classifier | | Research | Language researchers | Use it as a standard English baseline | Compare a new method against BERT | | Support | Teams handling English tickets | Train a classifier on its features | Route tickets by topic | If you want a model that writes text, you can skip it. The card points to GPT2-style models for that. ### Where to use it - Python with the transformers library, on Windows, macOS or Linux - Fine-tuning projects for classification, token classification and question answering - Quick masked-word tests through the fill-mask pipeline Jobs it does | Use case | Who | What they get back | | --- | --- | --- | | Masked word prediction | Developers | Ranked guesses for the hidden word | | Text features | Researchers | Feature vectors you can feed to a classifier | | Task fine-tuning | NLP teams | A base to train for classification or question answering | ### How to set it up Python with the transformers library 1. Install transformers. 2. Optionally download the model files by hand. 3. Load the model by name in your code. ```sh pip install -U huggingface_hub hf download google-bert/bert-base-uncased ``` ### How to use it Use the fill-mask pipeline for a quick test. The card says the raw model mainly serves as a starting point for fine-tuning on a task that looks at the whole sentence. ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='bert-base-uncased') >>> unmasker("Hello I'm a [MASK] model.") ``` ### Example You give the pipeline the sentence "Hello I'm a \[MASK\] model." and it returns ranked guesses for the hidden word. In the card's output the top guesses are fashion, role, new and super, each shown in lowercase. ### For newcomers and experts If you are new, think of BERT as a model that learned English by filling in blanks. The first small thing to try is the fill-mask pipeline with a sentence that has one hidden word. If you know the field, pretraining hides 15% of the words and adds next sentence prediction, which gives a bidirectional view of a sentence, unlike left-to-right models such as GPT. The trade-off is fit: it suits whole-sentence tasks after fine-tuning, not text generation. Hide 15% of the words in a text → Run the whole sentence through BERT → Predict the hidden words → Reuse the features for a task ### Good to know Parameters across BERT releases | Label | Value | | --- | --- | | bert-base-uncased | 110 M | | bert-large-uncased | 340 M | | bert-base-chinese | 110 M | | bert-base-multilingual-cased | 110 M | - Language: English only. - Case: uncased, and the card says the uncased models also strip accent markers. - Intended use: fine-tuning on whole-sentence tasks. - Size: about 440 MB in F32. - License: apache-2.0. - Cost to run: no API key, account or paid service is named. - Data it reaches: you download the model from Hugging Face, and the card names no other access. - Not for: text generation, where the card suggests a model like GPT2. ## README ````markdown # BERT base model (uncased) Fills in masked words and extracts text features for English. The uncased BERT base model from Google, meant to be fine-tuned for classification, tagging and question answering. Made by google-bert on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This is the base BERT model for English, pretrained on raw English text by predicting masked words and by judging whether two sentences follow each other. It is uncased, so english and English are treated alike. It has 110M parameters. Who it suits: It suits developers and researchers who fine-tune a model for tasks that read whole sentences. People have published 7,169 fine-tuned versions of it. ```table Title: Who runs it Industry | Who uses it | How they use it | Example Software | NLP developers | Fine-tune it for sequence or token classification | A sentiment or topic classifier Research | Language researchers | Use it as a standard English baseline | Compare a new method against BERT Support | Teams handling English tickets | Train a classifier on its features | Route tickets by topic ``` If you want a model that writes text, you can skip it. The card points to GPT2-style models for that. Where to use it: - Python with the transformers library, on Windows, macOS or Linux - Fine-tuning projects for classification, token classification and question answering - Quick masked-word tests through the fill-mask pipeline ```table Title: Jobs it does Use case | Who | What they get back Masked word prediction | Developers | Ranked guesses for the hidden word Text features | Researchers | Feature vectors you can feed to a classifier Task fine-tuning | NLP teams | A base to train for classification or question answering ``` How to set it up: Python with the transformers library 1. Install transformers. 2. Optionally download the model files by hand. 3. Load the model by name in your code. ```sh pip install -U huggingface_hub hf download google-bert/bert-base-uncased ``` How to use it: Use the fill-mask pipeline for a quick test. The card says the raw model mainly serves as a starting point for fine-tuning on a task that looks at the whole sentence. ```python >>> from transformers import pipeline >>> unmasker = pipeline('fill-mask', model='bert-base-uncased') >>> unmasker("Hello I'm a [MASK] model.") ``` Example: You give the pipeline the sentence "Hello I'm a [MASK] model." and it returns ranked guesses for the hidden word. In the card's output the top guesses are fashion, role, new and super, each shown in lowercase. For newcomers and experts: If you are new, think of BERT as a model that learned English by filling in blanks. The first small thing to try is the fill-mask pipeline with a sentence that has one hidden word. If you know the field, pretraining hides 15% of the words and adds next sentence prediction, which gives a bidirectional view of a sentence, unlike left-to-right models such as GPT. The trade-off is fit: it suits whole-sentence tasks after fine-tuning, not text generation. ```flow Hide 15% of the words in a text Run the whole sentence through BERT Predict the hidden words Reuse the features for a task ``` Good to know: ```chart Title: Parameters across BERT releases bert-base-uncased: 110 M bert-large-uncased: 340 M bert-base-chinese: 110 M bert-base-multilingual-cased: 110 M ``` - Language: English only. - Case: uncased, and the card says the uncased models also strip accent markers. - Intended use: fine-tuning on whole-sentence tasks. - Size: about 440 MB in F32. - License: apache-2.0. - Cost to run: no API key, account or paid service is named. - Data it reaches: you download the model from Hugging Face, and the card names no other access. - Not for: text generation, where the card suggests a model like GPT2. ## On Hugging Face, 13 November 2026 - Task: fill mask - Library: transformers - Parameters: 110M - Weights: about 440 MB in F32; about 55 MB at 4-bit (estimate) - Formats: Safetensors - Downloads in the last 30 days: 31,346,528 - Likes: 3,071 - License: apache-2.0 - Languages: en - Quantized versions: 46 - Fine-tunes: 7,254 - Tags: transformers, pytorch, rust, coreml, onnx, safetensors, bert, fill-mask, exbert ## Links - Model: https://huggingface.co/google-bert/bert-base-uncased - Files: https://huggingface.co/google-bert/bert-base-uncased/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download google-bert/bert-base-uncased ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [google-bert/bert-base-uncased on Hugging Face](https://huggingface.co/google-bert/bert-base-uncased) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | Parameters | License | Last change | | --- | --- | --- | --- | --- | --- | | BERT base model (uncased) (this page) | 31,346,528 | 3,071 | 110M | apache-2.0 | 2024-02-19 | | [DistilBERT base uncased](https://mindket.com/p/1f7983ee-5699-4a51-89df-d2040b3038ba) | 5,452,853 | 1,148 | 67M | apache-2.0 | 2024-05-06 | | [GPT-2](https://mindket.com/p/c513092f-bbe7-4baa-989f-dfdc12a2b725) | 32,892,223 | 3,932 | 137M | mit | 2024-02-19 | | [all-MiniLM-L6-v2](https://mindket.com/p/ee5187e2-9f20-47be-ae7e-3a6007276a39) | 174,740,184 | 6,104 | 22.7M | apache-2.0 | 2026-06-01 | | [BERT multilingual base model (cased)](https://mindket.com/p/d65751a4-3ba8-4723-a545-f14db7a02c6a) | 1,539,340 | 623 | 179M | apache-2.0 | 2024-02-19 | | [bert-base-chinese](https://mindket.com/p/38d6215d-53a8-4176-a151-492374bad343) | 353,460 | 1,502 | 103M | apache-2.0 | 2025-07-03 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2024-02-19 - First published: 2022-03-02 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open google-bert/bert-base-uncased on Hugging Face](https://huggingface.co/google-bert/bert-base-uncased) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/d5887db0-760c-4639-8457-d0da6a3a2699) - [Its page on Mindket](https://mindket.com/p/d5887db0-760c-4639-8457-d0da6a3a2699)