Upload model
Browse files- config.json +19 -30
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -2,56 +2,45 @@
|
|
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":
|
13 |
-
"
|
14 |
-
"classifier_dropout": 0.1,
|
15 |
"d_model": 768,
|
16 |
-
"decoder_attention_heads":
|
17 |
-
"decoder_ffn_dim":
|
18 |
"decoder_layerdrop": 0.0,
|
19 |
-
"decoder_layers":
|
20 |
-
"decoder_start_token_id":
|
21 |
-
"do_blenderbot_90_layernorm": false,
|
22 |
"dropout": 0.1,
|
23 |
-
"encoder_attention_heads":
|
24 |
-
"encoder_ffn_dim":
|
25 |
"encoder_layerdrop": 0.0,
|
26 |
-
"encoder_layers":
|
27 |
-
"eos_token_id":
|
28 |
-
"
|
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": "
|
35 |
-
"1": "
|
|
|
36 |
},
|
37 |
"init_std": 0.02,
|
38 |
"is_encoder_decoder": true,
|
39 |
-
"kobart_version": 1.0,
|
40 |
"label2id": {
|
41 |
-
"
|
42 |
-
"
|
|
|
43 |
},
|
44 |
"max_position_embeddings": 1026,
|
45 |
"model_type": "bart",
|
46 |
-
"
|
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.
|
55 |
"use_cache": true,
|
56 |
"vocab_size": 30000
|
57 |
}
|
|
|
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": 2,
|
11 |
+
"classifier_dropout": 0.0,
|
|
|
12 |
"d_model": 768,
|
13 |
+
"decoder_attention_heads": 12,
|
14 |
+
"decoder_ffn_dim": 4096,
|
15 |
"decoder_layerdrop": 0.0,
|
16 |
+
"decoder_layers": 9,
|
17 |
+
"decoder_start_token_id": 2,
|
|
|
18 |
"dropout": 0.1,
|
19 |
+
"encoder_attention_heads": 12,
|
20 |
+
"encoder_ffn_dim": 4096,
|
21 |
"encoder_layerdrop": 0.0,
|
22 |
+
"encoder_layers": 3,
|
23 |
+
"eos_token_id": 2,
|
24 |
+
"forced_eos_token_id": 2,
|
|
|
|
|
|
|
|
|
25 |
"id2label": {
|
26 |
+
"0": "LABEL_0",
|
27 |
+
"1": "LABEL_1",
|
28 |
+
"2": "LABEL_2"
|
29 |
},
|
30 |
"init_std": 0.02,
|
31 |
"is_encoder_decoder": true,
|
|
|
32 |
"label2id": {
|
33 |
+
"LABEL_0": 0,
|
34 |
+
"LABEL_1": 1,
|
35 |
+
"LABEL_2": 2
|
36 |
},
|
37 |
"max_position_embeddings": 1026,
|
38 |
"model_type": "bart",
|
39 |
+
"num_hidden_layers": 2,
|
|
|
|
|
40 |
"pad_token_id": 3,
|
41 |
"scale_embedding": false,
|
|
|
|
|
42 |
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.34.1",
|
44 |
"use_cache": true,
|
45 |
"vocab_size": 30000
|
46 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:472d5e776407c68fefbb4958b275c0fdcfaee8488e93c6c651d4787c425c7699
|
3 |
+
size 495523222
|