Instructions to use ELiRF/NASCA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ELiRF/NASCA 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="ELiRF/NASCA")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ELiRF/NASCA") model = AutoModelForSeq2SeqLM.from_pretrained("ELiRF/NASCA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
José Ángel González commited on
Commit ·
3960e5f
1
Parent(s): 7c5780e
Update config.json
Browse filesParameters of `generate` in config
- config.json +8 -1
config.json
CHANGED
|
@@ -37,13 +37,20 @@
|
|
| 37 |
"task_specific_params": {
|
| 38 |
"summarization": {
|
| 39 |
"early_stopping": true,
|
| 40 |
-
"
|
| 41 |
"max_length": 150,
|
| 42 |
"min_length": 25,
|
| 43 |
"no_repeat_ngram_size": 3,
|
| 44 |
"num_beams": 4
|
| 45 |
}
|
| 46 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
"mask_sent_token_id": 6,
|
| 48 |
"mask_token_id": 5,
|
| 49 |
"max_position_embeddings": 512,
|
|
|
|
| 37 |
"task_specific_params": {
|
| 38 |
"summarization": {
|
| 39 |
"early_stopping": true,
|
| 40 |
+
"repetition_penalty": 2.0,
|
| 41 |
"max_length": 150,
|
| 42 |
"min_length": 25,
|
| 43 |
"no_repeat_ngram_size": 3,
|
| 44 |
"num_beams": 4
|
| 45 |
}
|
| 46 |
},
|
| 47 |
+
"early_stopping": true,
|
| 48 |
+
"repetition_penalty": 2.0,
|
| 49 |
+
"max_length": 150,
|
| 50 |
+
"min_length": 25,
|
| 51 |
+
"no_repeat_ngram_size": 3,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
|
| 54 |
"mask_sent_token_id": 6,
|
| 55 |
"mask_token_id": 5,
|
| 56 |
"max_position_embeddings": 512,
|