Instructions to use cijo-uc/layoutlm-funsd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cijo-uc/layoutlm-funsd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="cijo-uc/layoutlm-funsd")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("cijo-uc/layoutlm-funsd") model = AutoModelForTokenClassification.from_pretrained("cijo-uc/layoutlm-funsd", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from cijo-uc/layoutlm-funsd: direct link, hf CLI and curl.
- Browser
- Download file 3.61 kB
-
https://huggingface.co/cijo-uc/layoutlm-funsd/resolve/main/README.md
- Command line
-
hf download hf://cijo-uc/layoutlm-funsd/README.md
-
curl -L -o README.md https://huggingface.co/cijo-uc/layoutlm-funsd/resolve/main/README.md
3.61 kB
metadata
license: mit
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_trainer
datasets:
- funsd
model-index:
- name: layoutlm-funsd
results: []
layoutlm-funsd
This model is a fine-tuned version of microsoft/layoutlm-base-uncased on the funsd dataset. It achieves the following results on the evaluation set:
- Loss: 1.3476
- Answer: {'precision': 0.17894736842105263, 'recall': 0.3362175525339926, 'f1': 0.2335766423357664, 'number': 809}
- Header: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119}
- Question: {'precision': 0.27942998760842624, 'recall': 0.42347417840375584, 'f1': 0.33669279581933553, 'number': 1065}
- Overall Precision: 0.2307
- Overall Recall: 0.3628
- Overall F1: 0.2820
- Overall Accuracy: 0.4351
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|
| 1.7432 | 1.0 | 10 | 1.5651 | {'precision': 0.03228782287822878, 'recall': 0.04326328800988875, 'f1': 0.036978341257263604, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.18964259664478483, 'recall': 0.24413145539906103, 'f1': 0.2134646962233169, 'number': 1065} | 0.1202 | 0.1480 | 0.1326 | 0.3666 |
| 1.5478 | 2.0 | 20 | 1.4279 | {'precision': 0.13696715583508037, 'recall': 0.242274412855377, 'f1': 0.17500000000000002, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.25, 'recall': 0.3652582159624413, 'f1': 0.29683326974437235, 'number': 1065} | 0.1958 | 0.2935 | 0.2349 | 0.4085 |
| 1.4112 | 3.0 | 30 | 1.3476 | {'precision': 0.17894736842105263, 'recall': 0.3362175525339926, 'f1': 0.2335766423357664, 'number': 809} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 119} | {'precision': 0.27942998760842624, 'recall': 0.42347417840375584, 'f1': 0.33669279581933553, 'number': 1065} | 0.2307 | 0.3628 | 0.2820 | 0.4351 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2