twigs commited on
Commit
8039af2
1 Parent(s): 49181a9

Model saved in epoch 1

Browse files
Files changed (3) hide show
  1. config.json +38 -0
  2. generation_config.json +8 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "twigs/bigbird-pegasus-large",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "BigBirdPegasusForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_type": "block_sparse",
10
+ "block_size": 64,
11
+ "bos_token_id": 2,
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": 16,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "encoder_attention_heads": 16,
21
+ "encoder_ffn_dim": 4096,
22
+ "encoder_layerdrop": 0.0,
23
+ "encoder_layers": 16,
24
+ "eos_token_id": 1,
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
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.26.1",
35
+ "use_bias": false,
36
+ "use_cache": true,
37
+ "vocab_size": 96103
38
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.26.1"
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1d01507de5e9a89c4eebb0323b18aff43c8d706d2e96675a01786663d8847cc
3
+ size 1154136109