Gnanesh5 commited on
Commit
23213f7
1 Parent(s): 2c34246

Model save

Browse files
Files changed (3) hide show
  1. config.json +35 -18
  2. pytorch_model.bin +2 -2
  3. training_args.bin +1 -1
config.json CHANGED
@@ -1,27 +1,44 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
 
 
 
 
 
12
  "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
  "layer_norm_eps": 1e-12,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
- "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.25.1",
24
- "type_vocab_size": 2,
25
- "use_cache": true,
26
- "vocab_size": 30522
 
27
  }
 
1
  {
2
+ "_name_or_path": "xlnet-base-cased",
3
  "architectures": [
4
+ "XLNetForSequenceClassification"
5
  ],
6
+ "attn_type": "bi",
7
+ "bi_data": false,
8
+ "bos_token_id": 1,
9
+ "clamp_len": -1,
10
+ "d_head": 64,
11
+ "d_inner": 3072,
12
+ "d_model": 768,
13
+ "dropout": 0.1,
14
+ "end_n_top": 5,
15
+ "eos_token_id": 2,
16
+ "ff_activation": "gelu",
17
  "initializer_range": 0.02,
 
18
  "layer_norm_eps": 1e-12,
19
+ "mem_len": null,
20
+ "model_type": "xlnet",
21
+ "n_head": 12,
22
+ "n_layer": 12,
23
+ "pad_token_id": 5,
 
24
  "problem_type": "single_label_classification",
25
+ "reuse_len": null,
26
+ "same_length": false,
27
+ "start_n_top": 5,
28
+ "summary_activation": "tanh",
29
+ "summary_last_dropout": 0.1,
30
+ "summary_type": "last",
31
+ "summary_use_proj": true,
32
+ "task_specific_params": {
33
+ "text-generation": {
34
+ "do_sample": true,
35
+ "max_length": 250
36
+ }
37
+ },
38
  "torch_dtype": "float32",
39
  "transformers_version": "4.25.1",
40
+ "untie_r": true,
41
+ "use_mems_eval": true,
42
+ "use_mems_train": false,
43
+ "vocab_size": 32000
44
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df28a39f700cadab0cdbbb3d307e44ffcac107a823f9c8ca9d415289148cd7bf
3
- size 438006125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ccceee7fb3e92ac2ebfddba366ef97eaf4e5bd6b456f5f7d29c0e4ebedd791
3
+ size 469309853
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d3e04ac3d4dcd9d96e5aba12fee9cb37ac83dbaa451b770bace6b20772bd099
3
  size 3375
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf756aacf01fc100db7361089cc3dd4f18d0588ad079bf617bc5d4de124dd88d
3
  size 3375