Update config.json
Browse files- config.json +1 -34
config.json
CHANGED
@@ -1,56 +1,23 @@
|
|
1 |
{
|
2 |
-
"_num_labels": 2,
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bad_words_ids": null,
|
8 |
"bos_token_id": 0,
|
9 |
-
"decoder_start_token_id": null,
|
10 |
-
"do_sample": false,
|
11 |
-
"early_stopping": false,
|
12 |
"eos_token_id": 2,
|
13 |
-
"
|
14 |
"hidden_act": "gelu",
|
15 |
"hidden_dropout_prob": 0.1,
|
16 |
"hidden_size": 768,
|
17 |
-
"id2label": {
|
18 |
-
"0": "LABEL_0",
|
19 |
-
"1": "LABEL_1"
|
20 |
-
},
|
21 |
"initializer_range": 0.02,
|
22 |
"intermediate_size": 3072,
|
23 |
-
"is_decoder": false,
|
24 |
-
"is_encoder_decoder": false,
|
25 |
-
"label2id": {
|
26 |
-
"LABEL_0": 0,
|
27 |
-
"LABEL_1": 1
|
28 |
-
},
|
29 |
"layer_norm_eps": 1e-05,
|
30 |
-
"length_penalty": 1.0,
|
31 |
-
"max_length": 20,
|
32 |
"max_position_embeddings": 130,
|
33 |
-
"min_length": 0,
|
34 |
"model_type": "roberta",
|
35 |
-
"no_repeat_ngram_size": 0,
|
36 |
"num_attention_heads": 12,
|
37 |
-
"num_beams": 1,
|
38 |
"num_hidden_layers": 12,
|
39 |
-
"num_return_sequences": 1,
|
40 |
-
"output_attentions": false,
|
41 |
-
"output_hidden_states": false,
|
42 |
-
"output_past": true,
|
43 |
"pad_token_id": 1,
|
44 |
-
"prefix": null,
|
45 |
-
"pruned_heads": {},
|
46 |
-
"repetition_penalty": 1.0,
|
47 |
-
"task_specific_params": null,
|
48 |
-
"temperature": 1.0,
|
49 |
-
"top_k": 50,
|
50 |
-
"top_p": 1.0,
|
51 |
-
"torchscript": false,
|
52 |
"tokenizer_class": "BertweetTokenizer",
|
53 |
"type_vocab_size": 1,
|
54 |
-
"use_bfloat16": false,
|
55 |
"vocab_size": 64001
|
56 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"RobertaForMaskedLM"
|
4 |
],
|
5 |
"attention_probs_dropout_prob": 0.1,
|
|
|
6 |
"bos_token_id": 0,
|
|
|
|
|
|
|
7 |
"eos_token_id": 2,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
|
|
|
|
|
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 3072,
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"layer_norm_eps": 1e-05,
|
|
|
|
|
15 |
"max_position_embeddings": 130,
|
|
|
16 |
"model_type": "roberta",
|
|
|
17 |
"num_attention_heads": 12,
|
|
|
18 |
"num_hidden_layers": 12,
|
|
|
|
|
|
|
|
|
19 |
"pad_token_id": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
"tokenizer_class": "BertweetTokenizer",
|
21 |
"type_vocab_size": 1,
|
|
|
22 |
"vocab_size": 64001
|
23 |
}
|