Anhforth commited on
Commit
5b2a99c
1 Parent(s): ef3dd32

updated text encoder files

Browse files

Signed-off-by: Anhforth <yanzhaodong2021@163.com>

.gitignore ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ __pycache__
2
+ .idea/
3
+ logs/
4
+ test_tokenizer.py
5
+ samples_text2image/
6
+ generate_contexts/
7
+ venv/
8
+ *__pycache__
9
+ .DS_Store
10
+ .vscode
11
+ *.swo
12
+ *.swp
13
+ *log
14
+ build
15
+ dist
16
+ eazybigmodel.egg-info
17
+ flagai.egg-info
18
+ test_report
19
+ /data/
20
+ /tests/*/data
21
+ checkpoints
22
+ state_dict
23
+ checkpoints*
24
+ vocabs
25
+ tensorboard*
26
+ datasets
27
+ qqp
28
+ glm_large_qqp_pytorch
text_encoder/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "RobertaSeriesModelWithTransformation"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "learn_encoder": false,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "xlm-roberta",
19
+ "num_attention_heads": 16,
20
+ "num_hidden_layers": 24,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "pooler_fn": "cls",
24
+ "position_embedding_type": "absolute",
25
+ "project_dim": 768,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.24.0",
28
+ "type_vocab_size": 1,
29
+ "use_cache": true,
30
+ "vocab_size": 250002
31
+ }
text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7e5b6bef6737f75d01705be1d59295f5c9d84c10b9715a1610160fb646245d
3
+ size 2242851593
tokenizer/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "name_or_path": "/sharefs/baai-mrnd/yzd/test/xlm-roberta-large",
15
+ "pad_token": "<pad>",
16
+ "processor_class": "CHCLIPProcess",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }