Summarization
Transformers
PyTorch
TensorFlow
JAX
Rust
Safetensors
English
bart
text2text-generation
Eval Results (legacy)
Instructions to use facebook/bart-large-cnn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/bart-large-cnn 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="facebook/bart-large-cnn")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn") model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -12,7 +12,7 @@
|
|
| 12 |
"decoder_layers": 12,
|
| 13 |
"do_sample": false,
|
| 14 |
"dropout": 0.1,
|
| 15 |
-
"early_stopping":
|
| 16 |
"encoder_attention_heads": 16,
|
| 17 |
"encoder_ffn_dim": 4096,
|
| 18 |
"encoder_layerdrop": 0.0,
|
|
@@ -35,9 +35,9 @@
|
|
| 35 |
"LABEL_2": 2
|
| 36 |
},
|
| 37 |
"length_penalty": 2.0,
|
| 38 |
-
"max_length":
|
| 39 |
"max_position_embeddings": 1024,
|
| 40 |
-
"min_length":
|
| 41 |
"model_type": "bart",
|
| 42 |
"no_repeat_ngram_size": 3,
|
| 43 |
"num_beams": 4,
|
|
|
|
| 12 |
"decoder_layers": 12,
|
| 13 |
"do_sample": false,
|
| 14 |
"dropout": 0.1,
|
| 15 |
+
"early_stopping": true,
|
| 16 |
"encoder_attention_heads": 16,
|
| 17 |
"encoder_ffn_dim": 4096,
|
| 18 |
"encoder_layerdrop": 0.0,
|
|
|
|
| 35 |
"LABEL_2": 2
|
| 36 |
},
|
| 37 |
"length_penalty": 2.0,
|
| 38 |
+
"max_length": 142,
|
| 39 |
"max_position_embeddings": 1024,
|
| 40 |
+
"min_length": 56,
|
| 41 |
"model_type": "bart",
|
| 42 |
"no_repeat_ngram_size": 3,
|
| 43 |
"num_beams": 4,
|