hf-transformers-bot commited on
Commit
dc10512
·
verified ·
1 Parent(s): 1e132a6

Update tiny models for ProphetNetForConditionalGeneration

Browse files
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "add_cross_attention": true,
5
+ "architectures": [
6
+ "ProphetNetForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "decoder_ffn_dim": 32,
11
+ "decoder_start_token_id": 0,
12
+ "disable_ngram_loss": false,
13
+ "dropout": 0.1,
14
+ "dtype": "float32",
15
+ "encoder_ffn_dim": 32,
16
+ "eos_token_id": 2,
17
+ "eps": 0.0,
18
+ "hidden_size": 16,
19
+ "init_std": 0.02,
20
+ "is_decoder": false,
21
+ "is_encoder_decoder": true,
22
+ "max_position_embeddings": 200,
23
+ "model_type": "prophetnet",
24
+ "ngram": 2,
25
+ "num_buckets": 32,
26
+ "num_decoder_attention_heads": 4,
27
+ "num_decoder_layers": 2,
28
+ "num_encoder_attention_heads": 4,
29
+ "num_encoder_layers": 2,
30
+ "pad_token_id": 0,
31
+ "relative_max_distance": 128,
32
+ "tie_word_embeddings": true,
33
+ "transformers_version": "5.16.0.dev0",
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 2,
6
+ "output_attentions": false,
7
+ "output_hidden_states": false,
8
+ "pad_token_id": 0,
9
+ "transformers_version": "5.16.0.dev0",
10
+ "use_cache": true
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:694fbaea22b6ca90aecf0c746a4027b07108ba6244e5b4ba86d98e6183377648
3
+ size 2052496
prophetnet.tokenizer ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "2": {
12
+ "content": "[X_SEP]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "100": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "backend": "custom",
45
+ "clean_up_tokenization_spaces": true,
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "is_local": false,
49
+ "local_files_only": false,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 200,
52
+ "model_specific_special_tokens": {
53
+ "x_sep_token": "[X_SEP]"
54
+ },
55
+ "never_split": null,
56
+ "pad_token": "[PAD]",
57
+ "sep_token": "[SEP]",
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "ProphetNetTokenizer",
61
+ "unk_token": "[UNK]",
62
+ "x_sep_token": "[X_SEP]"
63
+ }