Instructions to use sshleifer/distilbart-cnn-12-6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sshleifer/distilbart-cnn-12-6 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="sshleifer/distilbart-cnn-12-6")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("sshleifer/distilbart-cnn-12-6") model = AutoModelForSeq2SeqLM.from_pretrained("sshleifer/distilbart-cnn-12-6", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Update config.json
#10
by bhumikak - opened
- config.json +2 -2
config.json
CHANGED
|
@@ -42,7 +42,7 @@
|
|
| 42 |
"LABEL_2": 2
|
| 43 |
},
|
| 44 |
"length_penalty": 2.0,
|
| 45 |
-
"max_length":
|
| 46 |
"max_position_embeddings": 1024,
|
| 47 |
"min_length": 56,
|
| 48 |
"model_type": "bart",
|
|
@@ -63,7 +63,7 @@
|
|
| 63 |
"summarization": {
|
| 64 |
"early_stopping": true,
|
| 65 |
"length_penalty": 2.0,
|
| 66 |
-
"max_length":
|
| 67 |
"min_length": 56,
|
| 68 |
"no_repeat_ngram_size": 3,
|
| 69 |
"num_beams": 4
|
|
|
|
| 42 |
"LABEL_2": 2
|
| 43 |
},
|
| 44 |
"length_penalty": 2.0,
|
| 45 |
+
"max_length": 40000,
|
| 46 |
"max_position_embeddings": 1024,
|
| 47 |
"min_length": 56,
|
| 48 |
"model_type": "bart",
|
|
|
|
| 63 |
"summarization": {
|
| 64 |
"early_stopping": true,
|
| 65 |
"length_penalty": 2.0,
|
| 66 |
+
"max_length": 40000,
|
| 67 |
"min_length": 56,
|
| 68 |
"no_repeat_ngram_size": 3,
|
| 69 |
"num_beams": 4
|