sobamchan commited on
Commit
d246ee9
1 Parent(s): 32437d1

Added model and config files

Browse files
README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ```py
2
+ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
3
+
4
+ tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large")
5
+ model = AutoModelForSeq2SeqLM.from_pretrained("vadis/bart_scitldr", use_auth_token=True)
6
+
7
+ text = "Abstract of a paper."
8
+ batch = tok(text, return_tensors="pt")
9
+ generated_ids = model.generate(batch["input_ids"])
10
+ print(tok.batch_decode(generated_ids, skip_special_tokens=True))
11
+ ```
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-large",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
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": 12,
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
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 12,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.17.0",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
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 sha256:890be02a840c39a4f7fb9ff0e696008f60d992eab3acb41ff8d37ca8f77d4924
3
+ size 1625551553
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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large", "tokenizer_class": "BartTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff