manojpreveen sshleifer commited on
Commit
22d1946
0 Parent(s):

Duplicate from sshleifer/distilbart-cnn-12-6

Browse files

Co-authored-by: Sam Shleifer <sshleifer@users.noreply.huggingface.co>

.gitattributes ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
2
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.h5 filter=lfs diff=lfs merge=lfs -text
5
+ *.tflite filter=lfs diff=lfs merge=lfs -text
6
+ *.tar.gz filter=lfs diff=lfs merge=lfs -text
7
+ *.ot filter=lfs diff=lfs merge=lfs -text
8
+ *.onnx filter=lfs diff=lfs merge=lfs -text
9
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - summarization
5
+ license: apache-2.0
6
+ datasets:
7
+ - cnn_dailymail
8
+ - xsum
9
+ thumbnail: https://huggingface.co/front/thumbnails/distilbart_medium.png
10
+ ---
11
+
12
+ ### Usage
13
+
14
+ This checkpoint should be loaded into `BartForConditionalGeneration.from_pretrained`. See the [BART docs](https://huggingface.co/transformers/model_doc/bart.html?#transformers.BartForConditionalGeneration) for more information.
15
+
16
+ ### Metrics for DistilBART models
17
+
18
+ | Model Name | MM Params | Inference Time (MS) | Speedup | Rouge 2 | Rouge-L |
19
+ |:---------------------------|------------:|----------------------:|----------:|----------:|----------:|
20
+ | distilbart-xsum-12-1 | 222 | 90 | 2.54 | 18.31 | 33.37 |
21
+ | distilbart-xsum-6-6 | 230 | 132 | 1.73 | 20.92 | 35.73 |
22
+ | distilbart-xsum-12-3 | 255 | 106 | 2.16 | 21.37 | 36.39 |
23
+ | distilbart-xsum-9-6 | 268 | 136 | 1.68 | 21.72 | 36.61 |
24
+ | bart-large-xsum (baseline) | 406 | 229 | 1 | 21.85 | 36.50 |
25
+ | distilbart-xsum-12-6 | 306 | 137 | 1.68 | 22.12 | 36.99 |
26
+ | bart-large-cnn (baseline) | 406 | 381 | 1 | 21.06 | 30.63 |
27
+ | distilbart-12-3-cnn | 255 | 214 | 1.78 | 20.57 | 30.00 |
28
+ | distilbart-12-6-cnn | 306 | 307 | 1.24 | 21.26 | 30.59 |
29
+ | distilbart-6-6-cnn | 230 | 182 | 2.09 | 20.17 | 29.70 |
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "extra_pos_embeddings": 2,
28
+ "force_bos_token_to_be_generated": true,
29
+ "forced_bos_token_id": 0,
30
+ "forced_eos_token_id": 2,
31
+ "gradient_checkpointing": false,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1",
35
+ "2": "LABEL_2"
36
+ },
37
+ "init_std": 0.02,
38
+ "is_encoder_decoder": true,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_2": 2
43
+ },
44
+ "length_penalty": 2.0,
45
+ "max_length": 142,
46
+ "max_position_embeddings": 1024,
47
+ "min_length": 56,
48
+ "model_type": "bart",
49
+ "no_repeat_ngram_size": 3,
50
+ "normalize_before": false,
51
+ "normalize_embedding": true,
52
+ "num_beams": 4,
53
+ "num_hidden_layers": 12,
54
+ "output_past": true,
55
+ "pad_token_id": 1,
56
+ "prefix": " ",
57
+ "replacing_rate": 0,
58
+ "scale_embedding": false,
59
+ "static_position_embeddings": false,
60
+ "student_decoder_layers": null,
61
+ "student_encoder_layers": null,
62
+ "task_specific_params": {
63
+ "summarization": {
64
+ "early_stopping": true,
65
+ "length_penalty": 2.0,
66
+ "max_length": 142,
67
+ "min_length": 56,
68
+ "no_repeat_ngram_size": 3,
69
+ "num_beams": 4
70
+ }
71
+ },
72
+ "transformers_version": "4.7.0.dev0",
73
+ "use_cache": true,
74
+ "vocab_size": 50264
75
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e850d264574dac2076ae01ce78afe398ac02ac4b68e144feb9ca108bb5851c0
3
+ size 1222255172
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bac65d18c99463302d12ca75c2220ea714f9c81ce235f205fa818efe71df6ea
3
+ size 1222317369
rust_model.ot ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e589ff34942ff07948bbce579cf701cc19e1bfe370f4e4afaf24484ca5d2a2b
3
+ size 1634092538
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_max_length": 1024}
vocab.json ADDED
The diff for this file is too large to render. See raw diff