mehrdadazizi
commited on
Commit
•
6e229fb
1
Parent(s):
942a1ad
Upload 5 files
Browse files- config.json +33 -0
- model.safetensors +3 -0
- special_tokens_map.json +12 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mobilebert-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"MobileBertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_activation": false,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"embedding_size": 128,
|
10 |
+
"hidden_act": "relu",
|
11 |
+
"hidden_dropout_prob": 0.0,
|
12 |
+
"hidden_size": 512,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 512,
|
15 |
+
"intra_bottleneck_size": 128,
|
16 |
+
"key_query_shared_bottleneck": true,
|
17 |
+
"layer_norm_eps": 1e-12,
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "mobilebert",
|
20 |
+
"normalization_type": "no_norm",
|
21 |
+
"num_attention_heads": 4,
|
22 |
+
"num_feedforward_networks": 4,
|
23 |
+
"num_hidden_layers": 24,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.36.2",
|
27 |
+
"trigram_input": true,
|
28 |
+
"true_hidden_size": 128,
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_bottleneck": true,
|
31 |
+
"use_bottleneck_attention": false,
|
32 |
+
"vocab_size": 50000
|
33 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:837c734017579aa926b4e932f40412fd30745899b3ae3da646dedcb1813092c4
|
3 |
+
size 186496176
|
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[zwnj]",
|
4 |
+
"[user]",
|
5 |
+
"[httplink]"
|
6 |
+
],
|
7 |
+
"cls_token": "[CLS]",
|
8 |
+
"mask_token": "[MASK]",
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"unk_token": "[UNK]"
|
12 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[zwnj]",
|
4 |
+
"[user]",
|
5 |
+
"[httplink]"
|
6 |
+
],
|
7 |
+
"clean_up_tokenization_spaces": true,
|
8 |
+
"cls_token": "[CLS]",
|
9 |
+
"mask_token": "[MASK]",
|
10 |
+
"model_max_length": 512,
|
11 |
+
"pad_token": "[PAD]",
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"split_special_tokens": false,
|
14 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|