hf-transformers-bot
commited on
Commit
•
bc3a3ff
1
Parent(s):
91b408d
Upload tiny models for FNetForNextSentencePrediction
Browse files- config.json +23 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +13 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"FNetForNextSentencePrediction"
|
4 |
+
],
|
5 |
+
"bos_token_id": 1,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 32,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 37,
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"model_type": "fnet",
|
15 |
+
"num_hidden_layers": 5,
|
16 |
+
"pad_token_id": 3,
|
17 |
+
"torch_dtype": "float32",
|
18 |
+
"tpu_short_seq_length": 7,
|
19 |
+
"transformers_version": "4.28.0.dev0",
|
20 |
+
"type_vocab_size": 16,
|
21 |
+
"use_tpu_fourier_optimizations": false,
|
22 |
+
"vocab_size": 32000
|
23 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:574808ea880a4e97bcd5008ed890ee661c53a1142acc17399d05525c8f572053
|
3 |
+
size 4244237
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": {
|
4 |
+
"content": "[MASK]",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f848afb4cb35389f15819aad6b9b4bb65d8b6cec9613b6145bea94b4a045ab6
|
3 |
+
size 708295
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"keep_accents": true,
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "[MASK]",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 512,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"remove_space": true,
|
17 |
+
"sep_token": "[SEP]",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"special_tokens_map_file": "./special_tokens_map.json",
|
20 |
+
"tokenizer_class": "FNetTokenizer",
|
21 |
+
"unk_token": "<unk>"
|
22 |
+
}
|