Summarization
Transformers
PyTorch
TensorFlow
JAX
Rust
English
bart
text2text-generation
Eval Results (legacy)
Instructions to use facebook/bart-large-xsum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/bart-large-xsum 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-xsum")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-xsum") model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-xsum") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit ·
d2e47ef
1
Parent(s): 4691813
Add evaluation results on the default config of xsum (#5)
Browse files- Add evaluation results on the default config of xsum (7421ec403505a71a1cea8b9097e15e384cbb7440)
- Fix merge conflict (805caaedbc72d1f85b3bdbe6e5d52336e0fe2923)
- Fix merge conflict v2 (5b380508a47d418ed40e453fcc4d99e9d4ee82cb)
Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -40,6 +40,39 @@ model-index:
|
|
| 40 |
type: gen_len
|
| 41 |
value: 27.4462
|
| 42 |
verified: true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
---
|
| 44 |
### Bart model finetuned on xsum
|
| 45 |
|
|
|
|
| 40 |
type: gen_len
|
| 41 |
value: 27.4462
|
| 42 |
verified: true
|
| 43 |
+
- task:
|
| 44 |
+
type: summarization
|
| 45 |
+
name: Summarization
|
| 46 |
+
dataset:
|
| 47 |
+
name: xsum
|
| 48 |
+
type: xsum
|
| 49 |
+
config: default
|
| 50 |
+
split: test
|
| 51 |
+
metrics:
|
| 52 |
+
- name: ROUGE-1
|
| 53 |
+
type: rouge
|
| 54 |
+
value: 45.4525
|
| 55 |
+
verified: true
|
| 56 |
+
- name: ROUGE-2
|
| 57 |
+
type: rouge
|
| 58 |
+
value: 22.3455
|
| 59 |
+
verified: true
|
| 60 |
+
- name: ROUGE-L
|
| 61 |
+
type: rouge
|
| 62 |
+
value: 37.2302
|
| 63 |
+
verified: true
|
| 64 |
+
- name: ROUGE-LSUM
|
| 65 |
+
type: rouge
|
| 66 |
+
value: 37.2323
|
| 67 |
+
verified: true
|
| 68 |
+
- name: loss
|
| 69 |
+
type: loss
|
| 70 |
+
value: 2.3128726482391357
|
| 71 |
+
verified: true
|
| 72 |
+
- name: gen_len
|
| 73 |
+
type: gen_len
|
| 74 |
+
value: 25.5435
|
| 75 |
+
verified: true
|
| 76 |
---
|
| 77 |
### Bart model finetuned on xsum
|
| 78 |
|