Instructions to use facebook/bart-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/bart-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="facebook/bart-large")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large") model = AutoModel.from_pretrained("facebook/bart-large", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +11 -0
config.json
CHANGED
|
@@ -12,6 +12,7 @@
|
|
| 12 |
"decoder_ffn_dim": 4096,
|
| 13 |
"decoder_layerdrop": 0.0,
|
| 14 |
"decoder_layers": 12,
|
|
|
|
| 15 |
"do_sample": false,
|
| 16 |
"dropout": 0.1,
|
| 17 |
"encoder_attention_heads": 16,
|
|
@@ -45,6 +46,16 @@
|
|
| 45 |
"prefix": " ",
|
| 46 |
"pruned_heads": {},
|
| 47 |
"repetition_penalty": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
"temperature": 1.0,
|
| 49 |
"top_k": 50,
|
| 50 |
"top_p": 1.0,
|
|
|
|
| 12 |
"decoder_ffn_dim": 4096,
|
| 13 |
"decoder_layerdrop": 0.0,
|
| 14 |
"decoder_layers": 12,
|
| 15 |
+
"decoder_start_token_id": 2,
|
| 16 |
"do_sample": false,
|
| 17 |
"dropout": 0.1,
|
| 18 |
"encoder_attention_heads": 16,
|
|
|
|
| 46 |
"prefix": " ",
|
| 47 |
"pruned_heads": {},
|
| 48 |
"repetition_penalty": 1.0,
|
| 49 |
+
"task_specific_params": {
|
| 50 |
+
"summarization": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"length_penalty": 2.0,
|
| 53 |
+
"max_length": 142,
|
| 54 |
+
"min_length": 56,
|
| 55 |
+
"no_repeat_ngram_size": 3,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
}
|
| 58 |
+
},
|
| 59 |
"temperature": 1.0,
|
| 60 |
"top_k": 50,
|
| 61 |
"top_p": 1.0,
|