Hugging Face's logo

crumb
/
enc-dec-test

Text2Text Generation
Transformers
Safetensors
encoder-decoder
Inference Endpoints
Model card Files Community
crumb commited on
Commit
2562dcc
•
1 Parent(s): b99236a

Upload model

Browse files
Files changed (3) hide show
  1. config.json +168 -0
  2. generation_config.json +5 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "my-model",
3
+ "architectures": [
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,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
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,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "repetition_penalty": 1.0,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "sep_token_id": null,
68
+ "suppress_tokens": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tf_legacy_loss": false,
72
+ "tie_encoder_decoder": false,
73
+ "tie_word_embeddings": true,
74
+ "tokenizer_class": null,
75
+ "top_k": 50,
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,
96
+ "decoder_start_token_id": null,
97
+ "diversity_penalty": 0.0,
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,
141
+ "pruned_heads": {},
142
+ "remove_invalid_values": false,
143
+ "repetition_penalty": 1.0,
144
+ "return_dict": true,
145
+ "return_dict_in_generate": false,
146
+ "sep_token_id": null,
147
+ "suppress_tokens": null,
148
+ "task_specific_params": null,
149
+ "temperature": 1.0,
150
+ "tf_legacy_loss": false,
151
+ "tie_encoder_decoder": false,
152
+ "tie_word_embeddings": true,
153
+ "tokenizer_class": null,
154
+ "top_k": 50,
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,
162
+ "vocab_size": 52305
163
+ },
164
+ "is_encoder_decoder": true,
165
+ "model_type": "encoder-decoder",
166
+ "torch_dtype": "float32",
167
+ "transformers_version": "4.35.2"
168
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.35.2"
5
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5426aa2b8f8c66b153a08519df021bc0f5e47880175def3db80c91df54c9600d
3
+ size 981652956