baseok

README.md

@@ -1,3 +1,59 @@
 ---
+language: en
 license: mit
+pipeline_tag: document-question-answering
+tags:
+ - layoutlm
+ - document-question-answering
+ - pdf
+widget:
+- text: "What is the invoice number?"
+  src: "https://huggingface.co/spaces/impira/docquery/resolve/2359223c1837a7587402bda0f2643382a6eefeab/invoice.png"
+- text: "What is the purchase amount?"
+  src: "https://huggingface.co/spaces/impira/docquery/resolve/2359223c1837a7587402bda0f2643382a6eefeab/contract.jpeg"
 ---
+
+# LayoutLM for Visual Question Answering
+
+This is a fine-tuned version of the multi-modal [LayoutLM](https://aka.ms/layoutlm) model for the task of question answering on documents. It has been fine-tuned using both the [SQuAD2.0](https://huggingface.co/datasets/squad_v2) and [DocVQA](https://www.docvqa.org/) datasets.
+
+## Getting started with the model
+
+To run these examples, you must have [PIL](https://pillow.readthedocs.io/en/stable/installation.html), [pytesseract](https://pypi.org/project/pytesseract/), and [PyTorch](https://pytorch.org/get-started/locally/) installed in addition to [transformers](https://huggingface.co/docs/transformers/index).
+
+```python
+from transformers import pipeline
+
+nlp = pipeline(
+    "document-question-answering",
+    model="impira/layoutlm-document-qa",
+)
+
+nlp(
+    "https://templates.invoicehome.com/invoice-template-us-neat-750px.png",
+    "What is the invoice number?"
+)
+# {'score': 0.9943977, 'answer': 'us-001', 'start': 15, 'end': 15}
+
+nlp(
+    "https://miro.medium.com/max/787/1*iECQRIiOGTmEFLdWkVIH2g.jpeg",
+    "What is the purchase amount?"
+)
+# {'score': 0.9912159, 'answer': '$1,000,000,000', 'start': 97, 'end': 97}
+
+nlp(
+    "https://www.accountingcoach.com/wp-content/uploads/2013/10/income-statement-example@2x.png",
+    "What are the 2020 net sales?"
+)
+# {'score': 0.59147286, 'answer': '$ 3,750', 'start': 19, 'end': 20}
+```
+
+**NOTE**: This model and pipeline was recently landed in transformers via [PR #18407](https://github.com/huggingface/transformers/pull/18407) and [PR #18414](https://github.com/huggingface/transformers/pull/18414), so you'll need to use a recent version of transformers, for example:
+
+```bash
+pip install git+https://github.com/huggingface/transformers.git@2ef774211733f0acf8d3415f9284c49ef219e991
+```
+
+## About us
+
+This model was created by the team at [Impira](https://www.impira.com/).

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "impira/layoutlm-document-qa",
+  "architectures": [
+    "LayoutLMForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "model_type": "layoutlm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "RobertaTokenizer",
+  "transformers_version": "4.22.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4bbad3e4a1b5ae50c787b7afd6049a0bfa99fd823b50436e444e092ae2347b9
+size 511200628

pyproject.toml

@@ -0,0 +1,3 @@
+[tool.black]
+line-length = 119
+target-version = ['py35']

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8b7882db23c58763acd876f50d04e3f291c8845febd3556f26b91f4b73f7c9
+size 511244837

setup.cfg

@@ -0,0 +1,18 @@
+[isort]
+default_section = FIRSTPARTY
+ensure_newline_before_comments = True
+force_grid_wrap = 0
+include_trailing_comma = True
+known_first_party = transformers
+
+line_length = 119
+lines_after_imports = 2
+multi_line_output = 3
+use_parentheses = True
+
+[flake8]
+ignore = E203, E501, E741, W503, W605
+max-line-length = 119
+
+[tool:pytest]
+doctest_optionflags=NUMBER NORMALIZE_WHITESPACE ELLIPSIS

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b79d6d938ef00f3ef9666db0d12907855272a1c476145d1bd8440cfdb97e433
+size 511465184

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "add_prefix_space": true}