Hugging Face's logo

JetBrains-Research
/
cmg-race-without-history

Text2Text Generation
Transformers
PyTorch
code
English
t5
commit_message_generation
text-generation-inference
Inference Endpoints
Model card Files Community
saridormi commited on
Commit
23c3806
•
1 Parent(s): 8bcfccf

Add model and tokenizer files

Browse files
Files changed (8) hide show
  1. added_tokens.json +11 -0
  2. config.json +68 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +62 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +65 -0
  8. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<DELETE>": 32104,
3
+ "<DELETE_END>": 32105,
4
+ "<INSERT>": 32102,
5
+ "<INSERT_END>": 32103,
6
+ "<KEEP>": 32100,
7
+ "<KEEP_END>": 32101,
8
+ "<REPLACE_END>": 32108,
9
+ "<REPLACE_NEW>": 32107,
10
+ "<REPLACE_OLD>": 32106
11
+ }
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Salesforce/codet5-base",
3
+ "architectures": [
4
+ "RACE"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "d_ff": 3072,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 2,
14
+ "feed_forward_proj": "relu",
15
+ "gradient_checkpointing": false,
16
+ "id2label": {
17
+ "0": "LABEL_0"
18
+ },
19
+ "initializer_factor": 1.0,
20
+ "is_encoder_decoder": true,
21
+ "is_gated_act": false,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "layer_norm_epsilon": 1e-06,
26
+ "model_type": "t5",
27
+ "n_positions": 512,
28
+ "num_decoder_layers": 12,
29
+ "num_heads": 12,
30
+ "num_layers": 12,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "relative_attention_max_distance": 128,
34
+ "relative_attention_num_buckets": 32,
35
+ "task_specific_params": {
36
+ "summarization": {
37
+ "early_stopping": true,
38
+ "length_penalty": 2.0,
39
+ "max_length": 200,
40
+ "min_length": 30,
41
+ "no_repeat_ngram_size": 3,
42
+ "num_beams": 4,
43
+ "prefix": "summarize: "
44
+ },
45
+ "translation_en_to_de": {
46
+ "early_stopping": true,
47
+ "max_length": 300,
48
+ "num_beams": 4,
49
+ "prefix": "translate English to German: "
50
+ },
51
+ "translation_en_to_fr": {
52
+ "early_stopping": true,
53
+ "max_length": 300,
54
+ "num_beams": 4,
55
+ "prefix": "translate English to French: "
56
+ },
57
+ "translation_en_to_ro": {
58
+ "early_stopping": true,
59
+ "max_length": 300,
60
+ "num_beams": 4,
61
+ "prefix": "translate English to Romanian: "
62
+ }
63
+ },
64
+ "torch_dtype": "float32",
65
+ "transformers_version": "4.21.3",
66
+ "use_cache": true,
67
+ "vocab_size": 32109
68
+ }
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 sha256:08068e30dc63f87bf69a70facee85b2b4643c7764bdcc811538ca35db0d2e638
3
+ size 891645499
special_tokens_map.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<KEEP>",
4
+ "<KEEP_END>",
5
+ "<INSERT>",
6
+ "<INSERT_END>",
7
+ "<DELETE>",
8
+ "<DELETE_END>",
9
+ "<REPLACE_OLD>",
10
+ "<REPLACE_NEW>",
11
+ "<REPLACE_END>"
12
+ ],
13
+ "bos_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "cls_token": {
21
+ "content": "<s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "eos_token": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "mask_token": {
35
+ "content": "<mask>",
36
+ "lstrip": true,
37
+ "normalized": true,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "pad_token": {
42
+ "content": "<pad>",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "sep_token": {
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "unk_token": {
56
+ "content": "<unk>",
57
+ "lstrip": false,
58
+ "normalized": true,
59
+ "rstrip": false,
60
+ "single_word": false
61
+ }
62
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 512,
37
+ "name_or_path": "Salesforce/codet5-base",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "/Users/Alexandra.Eliseeva/.cache/huggingface/transformers/5941df5e4315c5ab63b7b2ac791fb0bf0f209744a055c06b43b5274849137cdd.b9905d0575bde443a20834122b6e2d48e853b2e36444ce98ddeb43c38097eb3f",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff