Update config.json
Browse files- config.json +30 -19
config.json
CHANGED
@@ -2,45 +2,56 @@
|
|
2 |
"_name_or_path": "Gunulhona/tb_pretrained_sts",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu_new",
|
|
|
|
|
5 |
"architectures": [
|
6 |
"BartModel"
|
7 |
],
|
8 |
"attention_dropout": 0.0,
|
9 |
"author": "Kevin Jung([email protected])",
|
10 |
-
"bos_token_id":
|
11 |
-
"
|
|
|
12 |
"d_model": 768,
|
13 |
-
"decoder_attention_heads":
|
14 |
-
"decoder_ffn_dim":
|
15 |
"decoder_layerdrop": 0.0,
|
16 |
-
"decoder_layers":
|
17 |
-
"decoder_start_token_id":
|
|
|
18 |
"dropout": 0.1,
|
19 |
-
"encoder_attention_heads":
|
20 |
-
"encoder_ffn_dim":
|
21 |
"encoder_layerdrop": 0.0,
|
22 |
-
"encoder_layers":
|
23 |
-
"eos_token_id":
|
24 |
-
"
|
|
|
|
|
|
|
|
|
25 |
"id2label": {
|
26 |
-
"0": "
|
27 |
-
"1": "
|
28 |
-
"2": "LABEL_2"
|
29 |
},
|
30 |
"init_std": 0.02,
|
31 |
"is_encoder_decoder": true,
|
|
|
32 |
"label2id": {
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"LABEL_2": 2
|
36 |
},
|
37 |
"max_position_embeddings": 1026,
|
38 |
"model_type": "bart",
|
39 |
-
"
|
|
|
|
|
40 |
"pad_token_id": 3,
|
41 |
"scale_embedding": false,
|
|
|
|
|
42 |
"torch_dtype": "float32",
|
43 |
-
"transformers_version": "4.
|
44 |
"use_cache": true,
|
45 |
"vocab_size": 30000
|
46 |
}
|
|
|
2 |
"_name_or_path": "Gunulhona/tb_pretrained_sts",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu_new",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
"BartModel"
|
9 |
],
|
10 |
"attention_dropout": 0.0,
|
11 |
"author": "Kevin Jung([email protected])",
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.1,
|
14 |
+
"classifier_dropout": 0.1,
|
15 |
"d_model": 768,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 3072,
|
18 |
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 1,
|
21 |
+
"do_blenderbot_90_layernorm": false,
|
22 |
"dropout": 0.1,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 1,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": false,
|
30 |
+
"forced_eos_token_id": 1,
|
31 |
+
"gradient_checkpointing": false,
|
32 |
+
"num_labels":2,
|
33 |
"id2label": {
|
34 |
+
"0": "Negative",
|
35 |
+
"1": "Positive"
|
|
|
36 |
},
|
37 |
"init_std": 0.02,
|
38 |
"is_encoder_decoder": true,
|
39 |
+
"kobart_version": 1.0,
|
40 |
"label2id": {
|
41 |
+
"Negative": 0,
|
42 |
+
"Positive": 1
|
|
|
43 |
},
|
44 |
"max_position_embeddings": 1026,
|
45 |
"model_type": "bart",
|
46 |
+
"normalize_before": false,
|
47 |
+
"normalize_embedding": true,
|
48 |
+
"num_hidden_layers": 6,
|
49 |
"pad_token_id": 3,
|
50 |
"scale_embedding": false,
|
51 |
+
"static_position_embeddings": false,
|
52 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
53 |
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.12.5",
|
55 |
"use_cache": true,
|
56 |
"vocab_size": 30000
|
57 |
}
|