hf-transformers-bot commited on
Commit
3c90cfb
·
verified ·
1 Parent(s): 782ca64

Update tiny models for ElectraForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "ElectraForCausalLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "embedding_size": 32,
11
+ "eos_token_id": null,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 32,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 37,
17
+ "is_decoder": true,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "electra",
21
+ "num_attention_heads": 4,
22
+ "num_hidden_layers": 2,
23
+ "pad_token_id": 0,
24
+ "summary_activation": "gelu",
25
+ "summary_last_dropout": 0.1,
26
+ "summary_type": "first",
27
+ "summary_use_proj": true,
28
+ "tie_word_embeddings": true,
29
+ "transformers_version": "5.16.0.dev0",
30
+ "type_vocab_size": 16,
31
+ "use_cache": true,
32
+ "vocab_size": 30522
33
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "5.16.0.dev0",
7
+ "use_cache": true
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8afcfb15d0e349ca1bb558b73221f70bb99d7e1ab499d3dc4286af706ccb3afb
3
+ size 4160264
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": true,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }