add model
Browse files- config.json +10 -10
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "swish",
|
5 |
"add_bias_logits": false,
|
@@ -10,28 +10,28 @@
|
|
10 |
"attention_dropout": 0.0,
|
11 |
"bad_words_ids": [
|
12 |
[
|
13 |
-
|
14 |
]
|
15 |
],
|
16 |
-
"bos_token_id":
|
17 |
"classifier_dropout": 0.0,
|
18 |
"d_model": 512,
|
19 |
"decoder_attention_heads": 8,
|
20 |
"decoder_ffn_dim": 2048,
|
21 |
"decoder_layerdrop": 0.0,
|
22 |
"decoder_layers": 6,
|
23 |
-
"decoder_start_token_id":
|
24 |
-
"decoder_vocab_size":
|
25 |
"do_blenderbot_90_layernorm": false,
|
26 |
"dropout": 0.1,
|
27 |
"encoder_attention_heads": 8,
|
28 |
"encoder_ffn_dim": 2048,
|
29 |
"encoder_layerdrop": 0.0,
|
30 |
"encoder_layers": 6,
|
31 |
-
"eos_token_id":
|
32 |
"extra_pos_embeddings": 2,
|
33 |
"force_bos_token_to_be_generated": false,
|
34 |
-
"forced_eos_token_id":
|
35 |
"id2label": {
|
36 |
"0": "LABEL_0",
|
37 |
"1": "LABEL_1",
|
@@ -51,12 +51,12 @@
|
|
51 |
"normalize_embedding": false,
|
52 |
"num_beams": 6,
|
53 |
"num_hidden_layers": 6,
|
54 |
-
"pad_token_id":
|
55 |
"scale_embedding": true,
|
56 |
"share_encoder_decoder_embeddings": true,
|
57 |
"static_position_embeddings": true,
|
58 |
"torch_dtype": "float32",
|
59 |
-
"transformers_version": "4.
|
60 |
"use_cache": true,
|
61 |
-
"vocab_size":
|
62 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "output/marian_base_bt_finetuned",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "swish",
|
5 |
"add_bias_logits": false,
|
|
|
10 |
"attention_dropout": 0.0,
|
11 |
"bad_words_ids": [
|
12 |
[
|
13 |
+
3
|
14 |
]
|
15 |
],
|
16 |
+
"bos_token_id": 1,
|
17 |
"classifier_dropout": 0.0,
|
18 |
"d_model": 512,
|
19 |
"decoder_attention_heads": 8,
|
20 |
"decoder_ffn_dim": 2048,
|
21 |
"decoder_layerdrop": 0.0,
|
22 |
"decoder_layers": 6,
|
23 |
+
"decoder_start_token_id": 2,
|
24 |
+
"decoder_vocab_size": 32000,
|
25 |
"do_blenderbot_90_layernorm": false,
|
26 |
"dropout": 0.1,
|
27 |
"encoder_attention_heads": 8,
|
28 |
"encoder_ffn_dim": 2048,
|
29 |
"encoder_layerdrop": 0.0,
|
30 |
"encoder_layers": 6,
|
31 |
+
"eos_token_id": 2,
|
32 |
"extra_pos_embeddings": 2,
|
33 |
"force_bos_token_to_be_generated": false,
|
34 |
+
"forced_eos_token_id": 2,
|
35 |
"id2label": {
|
36 |
"0": "LABEL_0",
|
37 |
"1": "LABEL_1",
|
|
|
51 |
"normalize_embedding": false,
|
52 |
"num_beams": 6,
|
53 |
"num_hidden_layers": 6,
|
54 |
+
"pad_token_id": 3,
|
55 |
"scale_embedding": true,
|
56 |
"share_encoder_decoder_embeddings": true,
|
57 |
"static_position_embeddings": true,
|
58 |
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.19.0.dev0",
|
60 |
"use_cache": true,
|
61 |
+
"vocab_size": 32000
|
62 |
}
|
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 sha256:090d4b2517ab767abd3c777f52566e9d51e95babbb439bb692cff69d79c04650
|
3 |
+
size 242305245
|