qywu commited on
Commit
c641701
1 Parent(s): e538404

Upload MemBartForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +38 -0
  2. generation_config.json +9 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "MemBartForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 0,
11
+ "d_model": 1024,
12
+ "decoder_attention_heads": 16,
13
+ "decoder_ffn_dim": 4096,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 12,
16
+ "decoder_start_token_id": 2,
17
+ "dropout": 0.0,
18
+ "encoder_attention_heads": 16,
19
+ "encoder_ffn_dim": 4096,
20
+ "encoder_layerdrop": 0.0,
21
+ "encoder_layers": 12,
22
+ "eos_token_id": 2,
23
+ "forced_eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "init_std": 0.001,
26
+ "is_encoder_decoder": true,
27
+ "max_position_embeddings": 1024,
28
+ "memory_len": 128,
29
+ "normalize_before": false,
30
+ "normalize_embedding": true,
31
+ "pad_token_id": 1,
32
+ "pretrained_name": "facebook/bart-large",
33
+ "scale_embedding": false,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.26.1",
36
+ "use_cache": true,
37
+ "vocab_size": 50265
38
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.26.1"
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b674fd1a231cf5c724c37481e163ac8b26ecd2fc3f7fabed7eae27d2cb69d9
3
+ size 2234953513