hf-transformers-bot
commited on
Commit
•
de52fba
1
Parent(s):
0615573
Upload tiny models for RemBertForTokenClassification
Browse files- .gitattributes +1 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- sentencepiece.model +3 -0
- special_tokens_map.json +9 -0
- tf_model.h5 +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +16 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tiny_models/rembert/RemBertForTokenClassification",
|
3 |
+
"architectures": [
|
4 |
+
"RemBertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 312,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"eos_token_id": 313,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 32,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"input_embedding_size": 18,
|
15 |
+
"intermediate_size": 37,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 512,
|
18 |
+
"model_type": "rembert",
|
19 |
+
"num_attention_heads": 4,
|
20 |
+
"num_hidden_layers": 5,
|
21 |
+
"output_embedding_size": 43,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.28.0.dev0",
|
26 |
+
"type_vocab_size": 16,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 250300
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2b2dfcaba2da5aa2dbc76dbf793a39c67cb8ef592748b57496be954eeeb937e
|
3 |
+
size 18231231
|
sentencepiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
|
3 |
+
size 4697711
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb5371dbc001638b8d11b6c47fa8838b620eb1d2ae76cdec47210b412ff9011f
|
3 |
+
size 18327440
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64c2619f4b7bdfaa22061f522f23964fe13667c85aa1da5df5b191109e4d2a2c
|
3 |
+
size 16709845
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
5 |
+
"do_lower_case": false,
|
6 |
+
"eos_token": "[SEP]",
|
7 |
+
"keep_accents": true,
|
8 |
+
"mask_token": "[MASK]",
|
9 |
+
"model_max_length": 512,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"remove_space": true,
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"special_tokens_map_file": "/home/runner/.cache/huggingface/hub/models--google--rembert/snapshots/65da5133da36e29dfca67d4f0dd9f7f9db21b563/special_tokens_map.json",
|
14 |
+
"tokenizer_class": "RemBertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|