# deepset/bert-large-uncased-whole-word-masking-squad2

Model from Hugging Face for question answering: deepset/bert-large-uncased-whole-word-masking-squad2 · transformers

## Facts

- Type: LLM
- Task: question-answering
- Framework: transformers
- License: cc-by-4.0 — cc-by-4.0: commercial use, modification, and redistribution are permitted with attribution. (https://spdx.org/licenses/CC-by-4.0.html)
- Source: https://huggingface.co/deepset/bert-large-uncased-whole-word-masking-squad2
- Hosting: hosted (6 files)
- Files: 6 hosted of 12 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 6 files, 1.34 GB
- Full repo upstream: 6.6 GB
- Recommended file: 2.68 GB (2 files)
- Download: https://huggingbay.xyz/artifact/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2/download-plan)
- Per-file SHA-256: available for 6 of 6 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 192829
- Stars: 31
- Card completeness: 96%

## Description

External Hugging Face catalog record for deepset/bert-large-uncased-whole-word-masking-squad2. Task: question answering. Library: transformers. Languages: en. Datasets referenced by card metadata: squad_v2. Includes 12 model-card evaluation signals. Popularity signal at import: 205,789 downloads and 31 likes.

## Model Card Facts

- Declared license: cc-by-4.0
- Pipeline: question-answering
- Library: transformers
- Task categories: question-answering
- Languages: en
- Referenced datasets: squad_v2
- Model-index entries: deepset/bert-large-uncased-whole-word-masking-squad2
- Evaluation signals: 12 model-card eval results
- File hints: 12 upstream file samples

## Evaluation Signals

- squad_v2: Exact Match = 80.8846 (Question Answering)
- squad_v2: F1 = 83.8765 (Question Answering)
- squad: Exact Match = 85.904 (Question Answering)
- squad: F1 = 92.586 (Question Answering)
- adversarial_qa: Exact Match = 28.233 (Question Answering)
- adversarial_qa: F1 = 41.17 (Question Answering)
- squad_adversarial: Exact Match = 78.064 (Question Answering)
- squad_adversarial: F1 = 83.591 (Question Answering)
- squadshifts amazon: Exact Match = 65.615 (Question Answering)
- squadshifts amazon: F1 = 80.733 (Question Answering)

## Referenced Data

- Dataset: squad_v2

## File Hints

- .gitattributes (445 B)
- README.md (7.4 KB)
- added_tokens.json (2 B)
- config.json (540 B)
- flax_model.msgpack (1.2 GB) LFS
- model.safetensors (1.2 GB) LFS
- pytorch_model.bin (1.2 GB) LFS
- saved_model.tar.gz (1.2 GB) LFS
- special_tokens_map.json (112 B)
- tf_model.h5 (1.2 GB) LFS
- tokenizer_config.json (19 B)
- vocab.txt (226 KB)

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-09-21T00:58:13.587Z.
- Upstream license: cc-by-4.0. Mirror admission policy: permissive (owner policy; no license rights inferred).
- Model-index metadata found for deepset/bert-large-uncased-whole-word-masking-squad2.
- Model card references dataset context: squad_v2.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-deepset-bert-large-uncased-whole-word-masking-squad2&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-deepset-bert-large-uncased-whole-word-masking-squad2/decentralized-fallbacks