Hugging Face's logo

trl-internal-testing
/
tiny-Roberta-EncoderDecoderModel

Text2Text Generation
Transformers
PyTorch
encoder-decoder
Inference Endpoints
Model card Files Community
ybelkada commited on
Commit
9ba8af0
•
1 Parent(s): b974d61

Upload model

Browse files
Files changed (3) hide show
  1. config.json +170 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "hf-internal-testing/tiny-random-RobertaModel",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "RobertaModel"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": 0,
15
+ "chunk_size_feed_forward": 0,
16
+ "classifier_dropout": null,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 2,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "hidden_act": "gelu",
29
+ "hidden_dropout_prob": 0.1,
30
+ "hidden_size": 32,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 37,
37
+ "is_decoder": true,
38
+ "is_encoder_decoder": false,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1
42
+ },
43
+ "layer_norm_eps": 1e-12,
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 512,
47
+ "min_length": 0,
48
+ "model_type": "roberta",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_attention_heads": 4,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_hidden_layers": 5,
54
+ "num_return_sequences": 1,
55
+ "output_attentions": false,
56
+ "output_hidden_states": false,
57
+ "output_scores": false,
58
+ "pad_token_id": 1,
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": "float32",
78
+ "torchscript": false,
79
+ "type_vocab_size": 16,
80
+ "typical_p": 1.0,
81
+ "use_bfloat16": false,
82
+ "use_cache": true,
83
+ "vocab_size": 1024
84
+ },
85
+ "encoder": {
86
+ "_name_or_path": "hf-internal-testing/tiny-random-RobertaModel",
87
+ "add_cross_attention": false,
88
+ "architectures": [
89
+ "RobertaModel"
90
+ ],
91
+ "attention_probs_dropout_prob": 0.1,
92
+ "bad_words_ids": null,
93
+ "begin_suppress_tokens": null,
94
+ "bos_token_id": 0,
95
+ "chunk_size_feed_forward": 0,
96
+ "classifier_dropout": null,
97
+ "cross_attention_hidden_size": null,
98
+ "decoder_start_token_id": null,
99
+ "diversity_penalty": 0.0,
100
+ "do_sample": false,
101
+ "early_stopping": false,
102
+ "encoder_no_repeat_ngram_size": 0,
103
+ "eos_token_id": 2,
104
+ "exponential_decay_length_penalty": null,
105
+ "finetuning_task": null,
106
+ "forced_bos_token_id": null,
107
+ "forced_eos_token_id": null,
108
+ "hidden_act": "gelu",
109
+ "hidden_dropout_prob": 0.1,
110
+ "hidden_size": 32,
111
+ "id2label": {
112
+ "0": "LABEL_0",
113
+ "1": "LABEL_1"
114
+ },
115
+ "initializer_range": 0.02,
116
+ "intermediate_size": 37,
117
+ "is_decoder": false,
118
+ "is_encoder_decoder": false,
119
+ "label2id": {
120
+ "LABEL_0": 0,
121
+ "LABEL_1": 1
122
+ },
123
+ "layer_norm_eps": 1e-12,
124
+ "length_penalty": 1.0,
125
+ "max_length": 20,
126
+ "max_position_embeddings": 512,
127
+ "min_length": 0,
128
+ "model_type": "roberta",
129
+ "no_repeat_ngram_size": 0,
130
+ "num_attention_heads": 4,
131
+ "num_beam_groups": 1,
132
+ "num_beams": 1,
133
+ "num_hidden_layers": 5,
134
+ "num_return_sequences": 1,
135
+ "output_attentions": false,
136
+ "output_hidden_states": false,
137
+ "output_scores": false,
138
+ "pad_token_id": 1,
139
+ "position_embedding_type": "absolute",
140
+ "prefix": null,
141
+ "problem_type": null,
142
+ "pruned_heads": {},
143
+ "remove_invalid_values": false,
144
+ "repetition_penalty": 1.0,
145
+ "return_dict": true,
146
+ "return_dict_in_generate": false,
147
+ "sep_token_id": null,
148
+ "suppress_tokens": null,
149
+ "task_specific_params": null,
150
+ "temperature": 1.0,
151
+ "tf_legacy_loss": false,
152
+ "tie_encoder_decoder": false,
153
+ "tie_word_embeddings": true,
154
+ "tokenizer_class": null,
155
+ "top_k": 50,
156
+ "top_p": 1.0,
157
+ "torch_dtype": "float32",
158
+ "torchscript": false,
159
+ "type_vocab_size": 16,
160
+ "typical_p": 1.0,
161
+ "use_bfloat16": false,
162
+ "use_cache": true,
163
+ "vocab_size": 1024
164
+ },
165
+ "is_encoder_decoder": true,
166
+ "model_type": "encoder-decoder",
167
+ "tie_encoder_decoder": true,
168
+ "torch_dtype": "float32",
169
+ "transformers_version": "4.33.0.dev0"
170
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.33.0.dev0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed33a4bf8fb2e018a5514b48be2178fd93b7b4f07961c7479faf04f6ae246f5
3
+ size 491333