Transformers
PyTorch
English
t5
text2text-generation
semantic-role-labeling
question-answer generation
text-generation-inference
Instructions to use kleinay/qanom-seq2seq-model-baseline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kleinay/qanom-seq2seq-model-baseline with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("kleinay/qanom-seq2seq-model-baseline") model = AutoModelForSeq2SeqLM.from_pretrained("kleinay/qanom-seq2seq-model-baseline", device_map="auto") - Notebooks
- Google Colab
- Kaggle
rm import preprocessing
Browse files- pipeline.py +0 -1
pipeline.py
CHANGED
|
@@ -3,7 +3,6 @@ import json
|
|
| 3 |
from argparse import Namespace
|
| 4 |
from pathlib import Path
|
| 5 |
from transformers import Text2TextGenerationPipeline, AutoModelForSeq2SeqLM, AutoTokenizer
|
| 6 |
-
import preprocessing
|
| 7 |
|
| 8 |
def get_markers_for_model(is_t5_model: bool) -> Namespace:
|
| 9 |
special_tokens_constants = Namespace()
|
|
|
|
| 3 |
from argparse import Namespace
|
| 4 |
from pathlib import Path
|
| 5 |
from transformers import Text2TextGenerationPipeline, AutoModelForSeq2SeqLM, AutoTokenizer
|
|
|
|
| 6 |
|
| 7 |
def get_markers_for_model(is_t5_model: bool) -> Namespace:
|
| 8 |
special_tokens_constants = Namespace()
|