pszemraj commited on
Commit
1c32f6c
1 Parent(s): 82ced2a

Upload PegasusXForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +64 -0
  2. generation_config.json +15 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pszemraj/pegasus-x-large-book_synthsumm",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "PegasusXForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "block_size": 512,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 16,
20
+ "decoder_start_token_id": 0,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 16,
27
+ "encoder_no_repeat_ngram_size": 4,
28
+ "eos_token_id": 1,
29
+ "extra_pos_embeddings": 1,
30
+ "force_bos_token_to_be_generated": false,
31
+ "forced_eos_token_id": 1,
32
+ "gradient_checkpointing": false,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "length_penalty": 0.8,
46
+ "max_length": 512,
47
+ "max_position_embeddings": 16384,
48
+ "min_length": 8,
49
+ "model_type": "pegasus_x",
50
+ "no_repeat_ngram_size": 3,
51
+ "normalize_before": true,
52
+ "normalize_embedding": false,
53
+ "num_beams": 2,
54
+ "num_global_tokens": 128,
55
+ "num_hidden_layers": 16,
56
+ "pad_token_id": 0,
57
+ "scale_embedding": true,
58
+ "stagger_local_blocks": true,
59
+ "static_position_embeddings": true,
60
+ "torch_dtype": "bfloat16",
61
+ "transformers_version": "4.36.2",
62
+ "use_cache": true,
63
+ "vocab_size": 96103
64
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 0,
4
+ "early_stopping": true,
5
+ "encoder_no_repeat_ngram_size": 4,
6
+ "eos_token_id": 1,
7
+ "forced_eos_token_id": 1,
8
+ "length_penalty": 0.8,
9
+ "max_length": 512,
10
+ "min_length": 8,
11
+ "no_repeat_ngram_size": 3,
12
+ "num_beams": 2,
13
+ "pad_token_id": 0,
14
+ "transformers_version": "4.36.2"
15
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76a7f1c770a83c9fd8af06b6035202aede0bda9f884826097488087377e03426
3
+ size 1137395808