vasudevgupta commited on
Commit
f702a5f
1 Parent(s): ac656d5

add ckpt-300000

Browse files

config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu_fast",
4
+ "architectures": [
5
+ "BigBirdPegasusForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "attention_type": "block_sparse",
9
+ "block_size": 64,
10
+ "bos_token_id": 2,
11
+ "classifier_dropout": 0.0,
12
+ "d_model": 1024,
13
+ "decoder_attention_heads": 16,
14
+ "decoder_ffn_dim": 4096,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 16,
17
+ "decoder_start_token_id": 2,
18
+ "dropout": 0.1,
19
+ "encoder_attention_heads": 16,
20
+ "encoder_ffn_dim": 4096,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 16,
23
+ "eos_token_id": 1,
24
+ "gradient_checkpointing": false,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "max_position_embeddings": 4096,
28
+ "model_type": "bigbird_pegasus",
29
+ "num_hidden_layers": 16,
30
+ "num_random_blocks": 3,
31
+ "pad_token_id": 0,
32
+ "scale_embedding": true,
33
+ "transformers_version": "4.5.0.dev0",
34
+ "use_bias": false,
35
+ "use_cache": true,
36
+ "vocab_size": 96103,
37
+ "num_beams": 5,
38
+ "length_penalty": 0.8,
39
+ "tokenizer_class": "PegasusTokenizer"
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52a5b27a631d0ae2445e77ce97e9fcd7d13402079a741111eea024cc46e5c9d4
3
+ size 2308148159
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1b40df7e8825709c0172639c47338a68d5622e9e3b6cc0fae516537cae738b
3
+ size 1915455
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": "[MASK]", "mask_token_sent": null, "offset": 0, "additional_special_tokens": [], "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": "/home/patrick/.cache/huggingface/transformers/b548e984b09823ed5cea0e622c0ec194a7e07b3c5d2e6b48a7cde84bd179cc7c.4eda581f816a0a941629106f0338c957910ce4839ecf7e3e743bb79523bf7249", "name_or_path": "./bigbird-pegasus-large-arxiv", "model_max_length": 4096}