marjanfaizi commited on
Commit
f41dd93
·
verified ·
1 Parent(s): 07deaa9

Upload BartForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +42 -0
  2. generation_config.json +8 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/lareaulab/faizi/training_output/trias_vertebrate/checkpoint-630000",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "BartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 512,
12
+ "decoder_attention_heads": 8,
13
+ "decoder_ffn_dim": 2048,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 6,
16
+ "decoder_start_token_id": 1,
17
+ "dropout": 0.1,
18
+ "encoder_attention_heads": 8,
19
+ "encoder_ffn_dim": 2048,
20
+ "encoder_layerdrop": 0.0,
21
+ "encoder_layers": 6,
22
+ "eos_token_id": 1,
23
+ "forced_eos_token_id": 1,
24
+ "id2label": {
25
+ "0": "LABEL_0"
26
+ },
27
+ "init_std": 0.02,
28
+ "is_encoder_decoder": true,
29
+ "label2id": {
30
+ "LABEL_0": 0
31
+ },
32
+ "max_position_embeddings": 2048,
33
+ "model_type": "bart",
34
+ "num_hidden_layers": 6,
35
+ "pad_token_id": 2,
36
+ "scale_embedding": false,
37
+ "task": "pretraining",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.36.1",
40
+ "use_cache": true,
41
+ "vocab_size": 1657
42
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 1,
4
+ "eos_token_id": 1,
5
+ "forced_eos_token_id": 1,
6
+ "pad_token_id": 2,
7
+ "transformers_version": "4.36.1"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7aa3a80935c4ac88768615239d902e847e027341f4808ff916c26001c4e4a9d
3
+ size 188388860