Summarization
Transformers
PyTorch
TensorBoard
ONNX
Safetensors
German
bart
text2text-generation
Generated from Trainer
Eval Results (legacy)
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Shahm/bart-german")
model = AutoModelForSeq2SeqLM.from_pretrained("Shahm/bart-german", device_map="auto")Quick Links
mode-bart-deutsch
This model is a fine-tuned version of facebook/bart-base on the mlsum de dataset. It achieves the following results on the evaluation set:
- Loss: 1.2152
- Rouge1: 41.698
- Rouge2: 31.3548
- Rougel: 38.2817
- Rougelsum: 39.6349
- Gen Len: 63.1723
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: 5e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3
- Downloads last month
- 245
Model tree for Shahm/bart-german
Dataset used to train Shahm/bart-german
Evaluation results
- Rouge1 on mlsum deself-reported41.698
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("summarization", model="Shahm/bart-german")