mrl-nq models
Browse files- dpr-nq-d768_384_192_96_48/config.json +28 -0
- dpr-nq-d768_384_192_96_48/pytorch_model.bin +3 -0
- dpr-nq-d768_384_192_96_48_24/config.json +28 -0
- dpr-nq-d768_384_192_96_48_24/pytorch_model.bin +3 -0
- dpr-nq-d768_512_256_128_64/config.json +28 -0
- dpr-nq-d768_512_256_128_64/pytorch_model.bin +3 -0
- dpr-nq-d768_512_256_128_64_32/config.json +28 -0
- dpr-nq-d768_512_256_128_64_32/pytorch_model.bin +3 -0
dpr-nq-d768_384_192_96_48/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"Retriever"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"binarize_passage": true,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "retriever",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"retriever_model": "bert-base-uncased",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.26.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 30522
|
28 |
+
}
|
dpr-nq-d768_384_192_96_48/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93a17dbe6849535d16c8d6aa4d871ba51abcb11ec19bd9778cd0702e773d3c01
|
3 |
+
size 871312829
|
dpr-nq-d768_384_192_96_48_24/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"Retriever"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"binarize_passage": true,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "retriever",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"retriever_model": "bert-base-uncased",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.26.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 30522
|
28 |
+
}
|
dpr-nq-d768_384_192_96_48_24/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b692d1074482f9a09ebb19fba13cda05ef479913cb6743a47d138af9046b18f
|
3 |
+
size 871312829
|
dpr-nq-d768_512_256_128_64/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"Retriever"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"binarize_passage": true,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "retriever",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"retriever_model": "bert-base-uncased",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.26.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 30522
|
28 |
+
}
|
dpr-nq-d768_512_256_128_64/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5e74b1ca8f1a0879fe02e72c2e402efc6036b38f8cc1b9951001db14f276777
|
3 |
+
size 871312829
|
dpr-nq-d768_512_256_128_64_32/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"Retriever"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"binarize_passage": true,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "retriever",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"retriever_model": "bert-base-uncased",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.26.1",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 30522
|
28 |
+
}
|
dpr-nq-d768_512_256_128_64_32/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb4a19f91d8c41d788b525b8bd68d5e2e145065fc170bb3d13b26929205d2b75
|
3 |
+
size 871312829
|