Ubuntu commited on
Commit
164e40f
1 Parent(s): a2232af

add oyo mt team model

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForPreTraining"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "embedding_size": 768,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "electra",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "summary_activation": "gelu",
21
+ "summary_last_dropout": 0.1,
22
+ "summary_type": "first",
23
+ "summary_use_proj": true,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.31.0",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
events.out.tfevents.1693293434.n-978663a6-w-0.1.6.v2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6198dae0ee7fa46f8fae949902b663a91b8aac3e6629f0107f7e4261888433f
3
+ size 40698
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9032751819dc037716ddce034a0868ba69a46aec4c8692a5f73840d493a6a649
3
+ size 442538673
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "max_len": 512, "init_inputs": []}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff