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") - Inference
- Notebooks
- Google Colab
- Kaggle
Add evaluation results on the 3.0.0 config of cnn_dailymail
#3
by autoevaluator HF Staff - opened
README.md
CHANGED
|
@@ -1,9 +1,44 @@
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- summarization
|
| 4 |
-
|
| 5 |
license: mit
|
| 6 |
thumbnail: https://huggingface.co/front/thumbnails/facebook.png
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
# BART (large-sized model), fine-tuned on CNN Daily Mail
|
| 9 |
|
|
|
|
| 1 |
---
|
| 2 |
tags:
|
| 3 |
- summarization
|
|
|
|
| 4 |
license: mit
|
| 5 |
thumbnail: https://huggingface.co/front/thumbnails/facebook.png
|
| 6 |
+
model-index:
|
| 7 |
+
- name: facebook/bart-large-cnn
|
| 8 |
+
results:
|
| 9 |
+
- task:
|
| 10 |
+
type: summarization
|
| 11 |
+
name: Summarization
|
| 12 |
+
dataset:
|
| 13 |
+
name: cnn_dailymail
|
| 14 |
+
type: cnn_dailymail
|
| 15 |
+
config: 3.0.0
|
| 16 |
+
split: train
|
| 17 |
+
metrics:
|
| 18 |
+
- name: ROUGE-1
|
| 19 |
+
type: rouge
|
| 20 |
+
value: 42.9486
|
| 21 |
+
verified: true
|
| 22 |
+
- name: ROUGE-2
|
| 23 |
+
type: rouge
|
| 24 |
+
value: 20.8149
|
| 25 |
+
verified: true
|
| 26 |
+
- name: ROUGE-L
|
| 27 |
+
type: rouge
|
| 28 |
+
value: 30.6186
|
| 29 |
+
verified: true
|
| 30 |
+
- name: ROUGE-LSUM
|
| 31 |
+
type: rouge
|
| 32 |
+
value: 40.0376
|
| 33 |
+
verified: true
|
| 34 |
+
- name: loss
|
| 35 |
+
type: loss
|
| 36 |
+
value: 2.529000997543335
|
| 37 |
+
verified: true
|
| 38 |
+
- name: gen_len
|
| 39 |
+
type: gen_len
|
| 40 |
+
value: 78.5866
|
| 41 |
+
verified: true
|
| 42 |
---
|
| 43 |
# BART (large-sized model), fine-tuned on CNN Daily Mail
|
| 44 |
|