vedu commited on
Commit
72745a0
1 Parent(s): 24680cd

Upload 9 files

Browse files
README.md CHANGED
@@ -1,3 +1,62 @@
1
  ---
2
- license: afl-3.0
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ language: en
4
  ---
5
+
6
+ # BART (large-sized model)
7
+
8
+ BART model pre-trained on English language. It was introduced in the paper [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://arxiv.org/abs/1910.13461) by Lewis et al. and first released in [this repository](https://github.com/pytorch/fairseq/tree/master/examples/bart).
9
+
10
+ Disclaimer: The team releasing BART did not write a model card for this model so this model card has been written by the Hugging Face team.
11
+
12
+ ## Model description
13
+
14
+ BART is a transformer encoder-decoder (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.
15
+
16
+ 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).
17
+
18
+ ## Intended uses & limitations
19
+
20
+ You can use the raw model for text infilling. However, the model is mostly meant to be fine-tuned on a supervised dataset. See the [model hub](https://huggingface.co/models?search=bart) to look for fine-tuned versions on a task that interests you.
21
+
22
+ ### How to use
23
+
24
+ Here is how to use this model in PyTorch:
25
+
26
+ ```python
27
+ from transformers import BartTokenizer, BartModel
28
+
29
+ tokenizer = BartTokenizer.from_pretrained('facebook/bart-large')
30
+ model = BartModel.from_pretrained('facebook/bart-large')
31
+
32
+ inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
33
+ outputs = model(**inputs)
34
+
35
+ last_hidden_states = outputs.last_hidden_state
36
+ ```
37
+
38
+ ### BibTeX entry and citation info
39
+
40
+ ```bibtex
41
+ @article{DBLP:journals/corr/abs-1910-13461,
42
+ author = {Mike Lewis and
43
+ Yinhan Liu and
44
+ Naman Goyal and
45
+ Marjan Ghazvininejad and
46
+ Abdelrahman Mohamed and
47
+ Omer Levy and
48
+ Veselin Stoyanov and
49
+ Luke Zettlemoyer},
50
+ title = {{BART:} Denoising Sequence-to-Sequence Pre-training for Natural Language
51
+ Generation, Translation, and Comprehension},
52
+ journal = {CoRR},
53
+ volume = {abs/1910.13461},
54
+ year = {2019},
55
+ url = {http://arxiv.org/abs/1910.13461},
56
+ eprinttype = {arXiv},
57
+ eprint = {1910.13461},
58
+ timestamp = {Thu, 31 Oct 2019 14:02:26 +0100},
59
+ biburl = {https://dblp.org/rec/journals/corr/abs-1910-13461.bib},
60
+ bibsource = {dblp computer science bibliography, https://dblp.org}
61
+ }
62
+ ```
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "BartModel"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 0,
11
+ "classif_dropout": 0.1,
12
+ "classifier_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
+ "early_stopping": true,
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 4096,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
+ "eos_token_id": 2,
26
+ "forced_eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "num_beams": 4,
46
+ "num_hidden_layers": 12,
47
+ "pad_token_id": 1,
48
+ "scale_embedding": false,
49
+ "task_specific_params": {
50
+ "summarization": {
51
+ "length_penalty": 1.0,
52
+ "max_length": 128,
53
+ "min_length": 12,
54
+ "num_beams": 4
55
+ },
56
+ "summarization_cnn": {
57
+ "length_penalty": 2.0,
58
+ "max_length": 142,
59
+ "min_length": 56,
60
+ "num_beams": 4
61
+ },
62
+ "summarization_xsum": {
63
+ "length_penalty": 1.0,
64
+ "max_length": 62,
65
+ "min_length": 11,
66
+ "num_beams": 6
67
+ }
68
+ },
69
+ "transformers_version": "4.7.0.dev0",
70
+ "use_cache": true,
71
+ "vocab_size": 50265
72
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:954a481dd580ea66a4c221ffc66486f2dc6850f8012e16428a4f8d45f67718f9
3
+ size 812600864
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 sha256:167f36942ef5dd4ba793495a9212715ddef9a34085fb114f2768ce0aff3fe783
3
+ size 1625553741
rust_model.ot ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931cb440da07893989f9bd4a7f6cb7257b8eae104bcafeee69bb066c49ffb01c
3
+ size 2037059720
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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