Upload query_encoder with huggingface_hub
Browse files
query_encoder/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[qspan_start]": 28996, "[qspan_end]": 28997}
|
query_encoder/language_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1fe51fcc8d6e73103036fbb8555178de0de641f829b59e29bf3b699ee3ce506
|
3 |
+
size 433334705
|
query_encoder/language_model_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SpanBERT/spanbert-base-cased",
|
3 |
+
"attention_probs_dropout_prob": 0.1,
|
4 |
+
"classifier_dropout": null,
|
5 |
+
"directionality": "bidi",
|
6 |
+
"hidden_act": "gelu",
|
7 |
+
"hidden_dropout_prob": 0.1,
|
8 |
+
"hidden_size": 768,
|
9 |
+
"initializer_range": 0.02,
|
10 |
+
"intermediate_size": 3072,
|
11 |
+
"language": "english",
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"model_type": "bert",
|
15 |
+
"name": "CoreSearchQuestionEncoder",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"projection_dim": 0,
|
21 |
+
"revision": null,
|
22 |
+
"transformers_version": "4.13.0",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 28998
|
26 |
+
}
|
query_encoder/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
query_encoder/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "SpanBERT/spanbert-base-cased", "tokenizer_class": "BertTokenizer"}
|
query_encoder/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|