shauryakudiyal commited on
Commit
4a0181b
1 Parent(s): 39c64c7

Delete README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -59
README.md DELETED
@@ -1,59 +0,0 @@
1
- ---
2
- language:
3
- - en
4
- tags:
5
- - summarization
6
- thumbnail: https://huggingface.co/front/thumbnails/facebook.png
7
- datasets:
8
- - samsum
9
- model-index:
10
- - name: shauryakudiyal/fine-tuned-bart
11
- results:
12
- - task:
13
- type: summarization
14
- name: Summarization
15
- dataset:
16
- name: samsum
17
- type: samsum
18
- config: 3.0.0
19
- split: train
20
- metrics:
21
- - name: ROUGE-1
22
- type: rouge
23
- value: 42.437500
24
- verified: true
25
- - name: ROUGE-2
26
- type: rouge
27
- value: 18.446100
28
- verified: true
29
- - name: ROUGE-L
30
- type: rouge
31
- value: 32.710300
32
- verified: true
33
- - name: ROUGE-LSUM
34
- type: rouge
35
- value: 32.710300
36
- verified: true
37
- - name: loss
38
- type: loss
39
- value: 0.606930
40
- verified: true
41
- - name: gen_len
42
- type: gen_len
43
- value: 30.200000
44
- verified: true
45
- ---
46
- # BART (large-sized model), fine-tuned on SAMSUM
47
-
48
-
49
-
50
- ## Model description
51
-
52
- BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text.
53
-
54
- BART is particularly effective when fine-tuned for text generation (e.g. summarization, translation) but also works well for comprehension tasks (e.g. text classification, question answering). This particular checkpoint has been fine-tuned on CNN Daily Mail, a large collection of text-summary pairs.
55
-
56
- ## Intended uses & limitations
57
-
58
- You can use this model for text summarization.
59
-