Reality8081 commited on
Commit
f6a1395
·
verified ·
1 Parent(s): ecb3203

Upload model output from Kaggle

Browse files
Files changed (4) hide show
  1. config.json +70 -0
  2. model_state.bin +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +16 -0
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "BartModel"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 0,
11
+ "classif_dropout": 0.1,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 1024,
14
+ "decoder_attention_heads": 16,
15
+ "decoder_ffn_dim": 4096,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 12,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "dtype": "float16",
21
+ "encoder_attention_heads": 16,
22
+ "encoder_ffn_dim": 4096,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 12,
25
+ "eos_token_id": 2,
26
+ "gradient_checkpointing": false,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1",
30
+ "2": "LABEL_2"
31
+ },
32
+ "init_std": 0.02,
33
+ "is_decoder": false,
34
+ "is_encoder_decoder": true,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1,
38
+ "LABEL_2": 2
39
+ },
40
+ "max_position_embeddings": 1024,
41
+ "model_type": "bart",
42
+ "normalize_before": false,
43
+ "num_hidden_layers": 12,
44
+ "pad_token_id": 1,
45
+ "scale_embedding": false,
46
+ "task_specific_params": {
47
+ "summarization": {
48
+ "length_penalty": 1.0,
49
+ "max_length": 128,
50
+ "min_length": 12,
51
+ "num_beams": 4
52
+ },
53
+ "summarization_cnn": {
54
+ "length_penalty": 2.0,
55
+ "max_length": 142,
56
+ "min_length": 56,
57
+ "num_beams": 4
58
+ },
59
+ "summarization_xsum": {
60
+ "length_penalty": 1.0,
61
+ "max_length": 62,
62
+ "min_length": 11,
63
+ "num_beams": 6
64
+ }
65
+ },
66
+ "tie_word_embeddings": true,
67
+ "transformers_version": "5.2.0",
68
+ "use_cache": true,
69
+ "vocab_size": 50265
70
+ }
model_state.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765a1a0a5adcc88d6a556f46288499e0de88890eba1969e5939a73172d692227
3
+ size 814792291
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 1000000000000000019884624838656,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }