Summarization
Transformers
PyTorch
TensorFlow
JAX
TensorBoard
Italian
t5
text2text-generation
italian
sequence-to-sequence
wikipedia
efficient
wits
Eval Results (legacy)
text-generation-inference
Instructions to use gsarti/it5-efficient-small-el32-wiki-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gsarti/it5-efficient-small-el32-wiki-summarization with Transformers:
# 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="gsarti/it5-efficient-small-el32-wiki-summarization")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("gsarti/it5-efficient-small-el32-wiki-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("gsarti/it5-efficient-small-el32-wiki-summarization") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +11 -1
config.json
CHANGED
|
@@ -25,5 +25,15 @@
|
|
| 25 |
"torch_dtype": "float32",
|
| 26 |
"transformers_version": "4.15.0",
|
| 27 |
"use_cache": true,
|
| 28 |
-
"vocab_size": 32100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
}
|
|
|
|
| 25 |
"torch_dtype": "float32",
|
| 26 |
"transformers_version": "4.15.0",
|
| 27 |
"use_cache": true,
|
| 28 |
+
"vocab_size": 32100,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"summarization": {
|
| 31 |
+
"early_stopping": true,
|
| 32 |
+
"length_penalty": 2.0,
|
| 33 |
+
"max_length": 142,
|
| 34 |
+
"min_length": 56,
|
| 35 |
+
"no_repeat_ngram_size": 3,
|
| 36 |
+
"num_beams": 4
|
| 37 |
+
}
|
| 38 |
+
}
|
| 39 |
}
|