Hugging Face's logo

almanach
/
camembertav2-base-ckpts

Feature Extraction
Transformers
TensorBoard
French
deberta-v2
deberta-v3
debertav2
debertav3
camembert
Model card Files
xet
Metrics Community
wissamantoun commited on
Commit
085ad0b
·
verified ·
1 Parent(s): 44067e2

Upload folder using huggingface_hub

Browse files
Files changed (24) hide show
  1. post/ckpt-4000/pt/discriminator/config.json +41 -0
  2. post/ckpt-4000/pt/discriminator/pytorch_model.bin +3 -0
  3. post/ckpt-4000/pt/discriminator/special_tokens_map.json +51 -0
  4. post/ckpt-4000/pt/discriminator/tokenizer.json +0 -0
  5. post/ckpt-4000/pt/discriminator/tokenizer_config.json +57 -0
  6. post/ckpt-4000/pt/generator/config.json +38 -0
  7. post/ckpt-4000/pt/generator/pytorch_model.bin +3 -0
  8. post/ckpt-4000/pt/generator/special_tokens_map.json +51 -0
  9. post/ckpt-4000/pt/generator/tokenizer.json +0 -0
  10. post/ckpt-4000/pt/generator/tokenizer_config.json +57 -0
  11. post/ckpt-4000/tf/discriminator/config.json +36 -0
  12. post/ckpt-4000/tf/discriminator/special_tokens_map.json +51 -0
  13. post/ckpt-4000/tf/discriminator/tf_model.h5 +3 -0
  14. post/ckpt-4000/tf/discriminator/tokenizer.json +0 -0
  15. post/ckpt-4000/tf/discriminator/tokenizer_config.json +57 -0
  16. post/ckpt-4000/tf/discriminator/tokenizer_old.json +0 -0
  17. post/ckpt-4000/tf/discriminator/vocab.txt +0 -0
  18. post/ckpt-4000/tf/generator/config.json +33 -0
  19. post/ckpt-4000/tf/generator/special_tokens_map.json +51 -0
  20. post/ckpt-4000/tf/generator/tf_model.h5 +3 -0
  21. post/ckpt-4000/tf/generator/tokenizer.json +0 -0
  22. post/ckpt-4000/tf/generator/tokenizer_config.json +57 -0
  23. post/ckpt-4000/tf/generator/tokenizer_old.json +0 -0
  24. post/ckpt-4000/tf/generator/vocab.txt +0 -0
post/ckpt-4000/pt/discriminator/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch/camembertv2/runs/models/camembertav2-base-bf16/post/ckpt-4000/tf/discriminator",
3
+ "architectures": [
4
+ "DebertaV2Model"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 1,
8
+ "conv_act": "gelu",
9
+ "conv_kernel_size": 0,
10
+ "embedding_size": 768,
11
+ "eos_token_id": 2,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "layer_norm_eps": 1e-07,
18
+ "max_position_embeddings": 1024,
19
+ "max_relative_positions": -1,
20
+ "model_name": "camembertav2-base-bf16",
21
+ "model_type": "deberta-v2",
22
+ "norm_rel_ebd": "layer_norm",
23
+ "num_attention_heads": 12,
24
+ "num_hidden_layers": 12,
25
+ "pad_token_id": 0,
26
+ "pooler_dropout": 0,
27
+ "pooler_hidden_act": "gelu",
28
+ "pooler_hidden_size": 768,
29
+ "pos_att_type": [
30
+ "p2c",
31
+ "c2p"
32
+ ],
33
+ "position_biased_input": false,
34
+ "position_buckets": 256,
35
+ "relative_attention": true,
36
+ "share_att_key": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.18.0.dev0",
39
+ "type_vocab_size": 0,
40
+ "vocab_size": 32768
41
+ }
post/ckpt-4000/pt/discriminator/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c192d308e340611183a872cca05135b69e29afc6d0b20b23982ab0426aacff7
3
+ size 442553476
post/ckpt-4000/pt/discriminator/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true
8
+ },
9
+ "eos_token": {
10
+ "content": "[SEP]",
11
+ "single_word": false,
12
+ "lstrip": false,
13
+ "rstrip": false,
14
+ "normalized": true
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "single_word": false,
26
+ "lstrip": false,
27
+ "rstrip": false,
28
+ "normalized": true
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": true
36
+ },
37
+ "cls_token": {
38
+ "content": "[CLS]",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": true
43
+ },
44
+ "mask_token": {
45
+ "content": "[MASK]",
46
+ "single_word": false,
47
+ "lstrip": true,
48
+ "rstrip": false,
49
+ "normalized": true
50
+ }
51
+ }
post/ckpt-4000/pt/discriminator/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
post/ckpt-4000/pt/discriminator/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "[UNK]"
57
+ }
post/ckpt-4000/pt/generator/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch/camembertv2/runs/models/camembertav2-base-bf16/post/ckpt-4000/tf/generator",
3
+ "architectures": [
4
+ "DebertaV2Model"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "conv_act": "gelu",
8
+ "conv_kernel_size": 0,
9
+ "embedding_size": 768,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 256,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 1024,
15
+ "layer_norm_eps": 1e-07,
16
+ "max_position_embeddings": 1024,
17
+ "max_relative_positions": -1,
18
+ "model_type": "deberta-v2",
19
+ "norm_rel_ebd": "layer_norm",
20
+ "num_attention_heads": 4,
21
+ "num_hidden_layers": 12,
22
+ "pad_token_id": 0,
23
+ "pooler_dropout": 0,
24
+ "pooler_hidden_act": "gelu",
25
+ "pooler_hidden_size": 768,
26
+ "pos_att_type": [
27
+ "p2c",
28
+ "c2p"
29
+ ],
30
+ "position_biased_input": false,
31
+ "position_buckets": 256,
32
+ "relative_attention": true,
33
+ "share_att_key": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.18.0.dev0",
36
+ "type_vocab_size": 0,
37
+ "vocab_size": 32768
38
+ }
post/ckpt-4000/pt/generator/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3621f93c137f38648cc14c08d154a4154d60f858a843063947202d8d73d16fc5
3
+ size 139974151
post/ckpt-4000/pt/generator/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true
8
+ },
9
+ "eos_token": {
10
+ "content": "[SEP]",
11
+ "single_word": false,
12
+ "lstrip": false,
13
+ "rstrip": false,
14
+ "normalized": true
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "single_word": false,
26
+ "lstrip": false,
27
+ "rstrip": false,
28
+ "normalized": true
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": true
36
+ },
37
+ "cls_token": {
38
+ "content": "[CLS]",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": true
43
+ },
44
+ "mask_token": {
45
+ "content": "[MASK]",
46
+ "single_word": false,
47
+ "lstrip": true,
48
+ "rstrip": false,
49
+ "normalized": true
50
+ }
51
+ }
post/ckpt-4000/pt/generator/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
post/ckpt-4000/pt/generator/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "[UNK]"
57
+ }
post/ckpt-4000/tf/discriminator/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "bos_token_id": 1,
4
+ "conv_act": "gelu",
5
+ "conv_kernel_size": 0,
6
+ "embedding_size": 768,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-07,
14
+ "max_position_embeddings": 1024,
15
+ "max_relative_positions": -1,
16
+ "model_name": "camembertav2-base-bf16",
17
+ "model_type": "deberta-v2",
18
+ "norm_rel_ebd": "layer_norm",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 0,
22
+ "pooler_dropout": 0,
23
+ "pooler_hidden_act": "gelu",
24
+ "pooler_hidden_size": 768,
25
+ "pos_att_type": [
26
+ "p2c",
27
+ "c2p"
28
+ ],
29
+ "position_biased_input": false,
30
+ "position_buckets": 256,
31
+ "relative_attention": true,
32
+ "share_att_key": true,
33
+ "transformers_version": "4.18.0.dev0",
34
+ "type_vocab_size": 0,
35
+ "vocab_size": 32768
36
+ }
post/ckpt-4000/tf/discriminator/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true
8
+ },
9
+ "eos_token": {
10
+ "content": "[SEP]",
11
+ "single_word": false,
12
+ "lstrip": false,
13
+ "rstrip": false,
14
+ "normalized": true
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "single_word": false,
26
+ "lstrip": false,
27
+ "rstrip": false,
28
+ "normalized": true
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": true
36
+ },
37
+ "cls_token": {
38
+ "content": "[CLS]",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": true
43
+ },
44
+ "mask_token": {
45
+ "content": "[MASK]",
46
+ "single_word": false,
47
+ "lstrip": true,
48
+ "rstrip": false,
49
+ "normalized": true
50
+ }
51
+ }
post/ckpt-4000/tf/discriminator/tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:436c5ea3357bc8e2be90699519f2745fc2b03b397beed70cf5828de075dcaa9e
3
+ size 442732816
post/ckpt-4000/tf/discriminator/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
post/ckpt-4000/tf/discriminator/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "[UNK]"
57
+ }
post/ckpt-4000/tf/discriminator/tokenizer_old.json ADDED
The diff for this file is too large to render. See raw diff
 
post/ckpt-4000/tf/discriminator/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
post/ckpt-4000/tf/generator/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_probs_dropout_prob": 0.1,
3
+ "conv_act": "gelu",
4
+ "conv_kernel_size": 0,
5
+ "embedding_size": 768,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 256,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 1024,
11
+ "layer_norm_eps": 1e-07,
12
+ "max_position_embeddings": 1024,
13
+ "max_relative_positions": -1,
14
+ "model_type": "deberta-v2",
15
+ "norm_rel_ebd": "layer_norm",
16
+ "num_attention_heads": 4,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "pooler_dropout": 0,
20
+ "pooler_hidden_act": "gelu",
21
+ "pooler_hidden_size": 768,
22
+ "pos_att_type": [
23
+ "p2c",
24
+ "c2p"
25
+ ],
26
+ "position_biased_input": false,
27
+ "position_buckets": 256,
28
+ "relative_attention": true,
29
+ "share_att_key": true,
30
+ "transformers_version": "4.18.0.dev0",
31
+ "type_vocab_size": 0,
32
+ "vocab_size": 32768
33
+ }
post/ckpt-4000/tf/generator/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true
8
+ },
9
+ "eos_token": {
10
+ "content": "[SEP]",
11
+ "single_word": false,
12
+ "lstrip": false,
13
+ "rstrip": false,
14
+ "normalized": true
15
+ },
16
+ "unk_token": {
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "single_word": false,
26
+ "lstrip": false,
27
+ "rstrip": false,
28
+ "normalized": true
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": true
36
+ },
37
+ "cls_token": {
38
+ "content": "[CLS]",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": true
43
+ },
44
+ "mask_token": {
45
+ "content": "[MASK]",
46
+ "single_word": false,
47
+ "lstrip": true,
48
+ "rstrip": false,
49
+ "normalized": true
50
+ }
51
+ }
post/ckpt-4000/tf/generator/tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d193015aeea1fcb3bf8439d3592fc41c9c07eae1bcee1ff45e389b3be8609ffa
3
+ size 242567464
post/ckpt-4000/tf/generator/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
post/ckpt-4000/tf/generator/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "[UNK]"
57
+ }
post/ckpt-4000/tf/generator/tokenizer_old.json ADDED
The diff for this file is too large to render. See raw diff
 
post/ckpt-4000/tf/generator/vocab.txt ADDED
The diff for this file is too large to render. See raw diff