s-jse commited on
Commit
21b3d08
1 Parent(s): cee25d3

Add model weights

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<paraphrase>": 50265, "</paraphrase>": 50266}
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 12,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 12,
24
+ "eos_token_id": 2,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1",
28
+ "2": "LABEL_2"
29
+ },
30
+ "init_std": 0.02,
31
+ "is_encoder_decoder": true,
32
+ "label2id": {
33
+ "LABEL_0": 0,
34
+ "LABEL_1": 1,
35
+ "LABEL_2": 2
36
+ },
37
+ "max_position_embeddings": 1024,
38
+ "model_type": "bart",
39
+ "normalize_before": false,
40
+ "normalize_embedding": true,
41
+ "num_hidden_layers": 12,
42
+ "output_past": false,
43
+ "pad_token_id": 1,
44
+ "prefix": " ",
45
+ "scale_embedding": false,
46
+ "static_position_embeddings": false,
47
+ "task_specific_params": {
48
+ "summarization": {
49
+ "early_stopping": true,
50
+ "length_penalty": 2.0,
51
+ "max_length": 142,
52
+ "min_length": 56,
53
+ "no_repeat_ngram_size": 3,
54
+ "num_beams": 4
55
+ }
56
+ },
57
+ "vocab_size": 50267
58
+ }
eval_results.txt ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ perplexity = tensor(2.2904)
2
+ perplexity = tensor(2.1728)
3
+ perplexity = tensor(2.1122)
4
+ perplexity = tensor(2.0730)
5
+ perplexity = tensor(2.0399)
6
+ perplexity = tensor(2.0351)
7
+ perplexity = tensor(2.0084)
8
+ perplexity = tensor(1.9989)
9
+ perplexity = tensor(1.9771)
10
+ perplexity = tensor(1.9837)
11
+ perplexity = tensor(1.9665)
12
+ perplexity = tensor(1.9643)
13
+ perplexity = tensor(1.9716)
14
+ perplexity = tensor(1.9557)
15
+ perplexity = tensor(1.9557)
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:cf70c9040b50d5b558addad01e818198b57633f8d54027134ca1824fb1041458
3
+ size 1625577455
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["<paraphrase>", "</paraphrase>"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "model_max_length": 1024}
vocab.json ADDED
The diff for this file is too large to render. See raw diff