crumb commited on
Commit
cd99e7f
1 Parent(s): 6f4315e

Upload model

Browse files
Files changed (3) hide show
  1. config.json +37 -34
  2. generation_config.json +3 -1
  3. model.safetensors +2 -2
config.json CHANGED
@@ -4,13 +4,15 @@
4
  "EncoderDecoderModel"
5
  ],
6
  "decoder": {
7
- "_name_or_path": "",
8
  "add_cross_attention": true,
9
- "architectures": null,
10
- "attention_probs_dropout_prob": 0,
 
 
11
  "bad_words_ids": null,
12
  "begin_suppress_tokens": null,
13
- "bos_token_id": null,
14
  "chunk_size_feed_forward": 0,
15
  "classifier_dropout": null,
16
  "cross_attention_hidden_size": null,
@@ -19,43 +21,42 @@
19
  "do_sample": false,
20
  "early_stopping": false,
21
  "encoder_no_repeat_ngram_size": 0,
22
- "eos_token_id": null,
23
  "exponential_decay_length_penalty": null,
24
  "finetuning_task": null,
25
  "forced_bos_token_id": null,
26
  "forced_eos_token_id": null,
27
  "hidden_act": "gelu",
28
- "hidden_dropout_prob": 0,
29
- "hidden_size": 896,
30
  "id2label": {
31
  "0": "LABEL_0",
32
  "1": "LABEL_1"
33
  },
34
  "initializer_range": 0.02,
35
- "intermediate_size": 2240,
36
  "is_decoder": true,
37
  "is_encoder_decoder": false,
38
  "label2id": {
39
  "LABEL_0": 0,
40
  "LABEL_1": 1
41
  },
42
- "layer_norm_eps": 1e-12,
43
  "length_penalty": 1.0,
44
  "max_length": 20,
45
- "max_position_embeddings": 2048,
46
  "min_length": 0,
47
- "model_type": "bert",
48
  "no_repeat_ngram_size": 0,
49
- "num_attention_heads": 7,
50
  "num_beam_groups": 1,
51
  "num_beams": 1,
52
- "num_hidden_layers": 7,
53
  "num_return_sequences": 1,
54
  "output_attentions": false,
55
  "output_hidden_states": false,
56
  "output_scores": false,
57
- "pad_token_id": 0,
58
- "position_embed_type": "relative_key_query",
59
  "position_embedding_type": "absolute",
60
  "prefix": null,
61
  "problem_type": null,
@@ -76,20 +77,22 @@
76
  "top_p": 1.0,
77
  "torch_dtype": null,
78
  "torchscript": false,
79
- "type_vocab_size": 2,
80
  "typical_p": 1.0,
81
  "use_bfloat16": false,
82
  "use_cache": true,
83
  "vocab_size": 52305
84
  },
85
  "encoder": {
86
- "_name_or_path": "",
87
- "add_cross_attention": true,
88
- "architectures": null,
89
- "attention_probs_dropout_prob": 0,
 
 
90
  "bad_words_ids": null,
91
  "begin_suppress_tokens": null,
92
- "bos_token_id": null,
93
  "chunk_size_feed_forward": 0,
94
  "classifier_dropout": null,
95
  "cross_attention_hidden_size": null,
@@ -98,43 +101,42 @@
98
  "do_sample": false,
99
  "early_stopping": false,
100
  "encoder_no_repeat_ngram_size": 0,
101
- "eos_token_id": null,
102
  "exponential_decay_length_penalty": null,
103
  "finetuning_task": null,
104
  "forced_bos_token_id": null,
105
  "forced_eos_token_id": null,
106
  "hidden_act": "gelu",
107
- "hidden_dropout_prob": 0,
108
- "hidden_size": 896,
109
  "id2label": {
110
  "0": "LABEL_0",
111
  "1": "LABEL_1"
112
  },
113
  "initializer_range": 0.02,
114
- "intermediate_size": 2240,
115
- "is_decoder": true,
116
  "is_encoder_decoder": false,
117
  "label2id": {
118
  "LABEL_0": 0,
119
  "LABEL_1": 1
120
  },
121
- "layer_norm_eps": 1e-12,
122
  "length_penalty": 1.0,
123
  "max_length": 20,
124
- "max_position_embeddings": 2048,
125
  "min_length": 0,
126
- "model_type": "bert",
127
  "no_repeat_ngram_size": 0,
128
- "num_attention_heads": 7,
129
  "num_beam_groups": 1,
130
  "num_beams": 1,
131
- "num_hidden_layers": 7,
132
  "num_return_sequences": 1,
133
  "output_attentions": false,
134
  "output_hidden_states": false,
135
  "output_scores": false,
136
- "pad_token_id": 0,
137
- "position_embed_type": "relative_key_query",
138
  "position_embedding_type": "absolute",
139
  "prefix": null,
140
  "problem_type": null,
@@ -155,7 +157,7 @@
155
  "top_p": 1.0,
156
  "torch_dtype": null,
157
  "torchscript": false,
158
- "type_vocab_size": 2,
159
  "typical_p": 1.0,
160
  "use_bfloat16": false,
161
  "use_cache": true,
@@ -163,6 +165,7 @@
163
  },
164
  "is_encoder_decoder": true,
165
  "model_type": "encoder-decoder",
 
166
  "torch_dtype": "float32",
167
  "transformers_version": "4.35.2"
168
  }
 
4
  "EncoderDecoderModel"
5
  ],
6
  "decoder": {
7
+ "_name_or_path": "roberta-base",
8
  "add_cross_attention": true,
9
+ "architectures": [
10
+ "RobertaForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
  "bad_words_ids": null,
14
  "begin_suppress_tokens": null,
15
+ "bos_token_id": 0,
16
  "chunk_size_feed_forward": 0,
17
  "classifier_dropout": null,
18
  "cross_attention_hidden_size": null,
 
21
  "do_sample": false,
22
  "early_stopping": false,
23
  "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 2,
25
  "exponential_decay_length_penalty": null,
26
  "finetuning_task": null,
27
  "forced_bos_token_id": null,
28
  "forced_eos_token_id": null,
29
  "hidden_act": "gelu",
30
+ "hidden_dropout_prob": 0.1,
31
+ "hidden_size": 768,
32
  "id2label": {
33
  "0": "LABEL_0",
34
  "1": "LABEL_1"
35
  },
36
  "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
  "is_decoder": true,
39
  "is_encoder_decoder": false,
40
  "label2id": {
41
  "LABEL_0": 0,
42
  "LABEL_1": 1
43
  },
44
+ "layer_norm_eps": 1e-05,
45
  "length_penalty": 1.0,
46
  "max_length": 20,
47
+ "max_position_embeddings": 514,
48
  "min_length": 0,
49
+ "model_type": "roberta",
50
  "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 12,
52
  "num_beam_groups": 1,
53
  "num_beams": 1,
54
+ "num_hidden_layers": 12,
55
  "num_return_sequences": 1,
56
  "output_attentions": false,
57
  "output_hidden_states": false,
58
  "output_scores": false,
59
+ "pad_token_id": 1,
 
60
  "position_embedding_type": "absolute",
61
  "prefix": null,
62
  "problem_type": null,
 
77
  "top_p": 1.0,
78
  "torch_dtype": null,
79
  "torchscript": false,
80
+ "type_vocab_size": 1,
81
  "typical_p": 1.0,
82
  "use_bfloat16": false,
83
  "use_cache": true,
84
  "vocab_size": 52305
85
  },
86
  "encoder": {
87
+ "_name_or_path": "roberta-base",
88
+ "add_cross_attention": false,
89
+ "architectures": [
90
+ "RobertaForMaskedLM"
91
+ ],
92
+ "attention_probs_dropout_prob": 0.1,
93
  "bad_words_ids": null,
94
  "begin_suppress_tokens": null,
95
+ "bos_token_id": 0,
96
  "chunk_size_feed_forward": 0,
97
  "classifier_dropout": null,
98
  "cross_attention_hidden_size": null,
 
101
  "do_sample": false,
102
  "early_stopping": false,
103
  "encoder_no_repeat_ngram_size": 0,
104
+ "eos_token_id": 2,
105
  "exponential_decay_length_penalty": null,
106
  "finetuning_task": null,
107
  "forced_bos_token_id": null,
108
  "forced_eos_token_id": null,
109
  "hidden_act": "gelu",
110
+ "hidden_dropout_prob": 0.1,
111
+ "hidden_size": 768,
112
  "id2label": {
113
  "0": "LABEL_0",
114
  "1": "LABEL_1"
115
  },
116
  "initializer_range": 0.02,
117
+ "intermediate_size": 3072,
118
+ "is_decoder": false,
119
  "is_encoder_decoder": false,
120
  "label2id": {
121
  "LABEL_0": 0,
122
  "LABEL_1": 1
123
  },
124
+ "layer_norm_eps": 1e-05,
125
  "length_penalty": 1.0,
126
  "max_length": 20,
127
+ "max_position_embeddings": 514,
128
  "min_length": 0,
129
+ "model_type": "roberta",
130
  "no_repeat_ngram_size": 0,
131
+ "num_attention_heads": 12,
132
  "num_beam_groups": 1,
133
  "num_beams": 1,
134
+ "num_hidden_layers": 12,
135
  "num_return_sequences": 1,
136
  "output_attentions": false,
137
  "output_hidden_states": false,
138
  "output_scores": false,
139
+ "pad_token_id": 1,
 
140
  "position_embedding_type": "absolute",
141
  "prefix": null,
142
  "problem_type": null,
 
157
  "top_p": 1.0,
158
  "torch_dtype": null,
159
  "torchscript": false,
160
+ "type_vocab_size": 1,
161
  "typical_p": 1.0,
162
  "use_bfloat16": false,
163
  "use_cache": true,
 
165
  },
166
  "is_encoder_decoder": true,
167
  "model_type": "encoder-decoder",
168
+ "tie_encoder_decoder": true,
169
  "torch_dtype": "float32",
170
  "transformers_version": "4.35.2"
171
  }
generation_config.json CHANGED
@@ -1,5 +1,7 @@
1
  {
2
  "_from_model_config": true,
3
- "pad_token_id": 0,
 
 
4
  "transformers_version": "4.35.2"
5
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
  "transformers_version": "4.35.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5426aa2b8f8c66b153a08519df021bc0f5e47880175def3db80c91df54c9600d
3
- size 981652956
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5919bce141058d04a7002ec93d8ce415b11a84db5ff2c22d054f1228c35e4a8b
3
+ size 620935092