butterflytech commited on
Commit
69578e3
1 Parent(s): 61c86a5

Upload config.json

Browse files

replace config file with original file

Files changed (1) hide show
  1. config.json +55 -55
config.json CHANGED
@@ -1,57 +1,57 @@
1
  {
2
- "_name_or_path": "t5-base",
3
- "architectures": [
4
- "T5ForConditionalGeneration"
5
- ],
6
- "d_ff": 3072,
7
- "d_kv": 64,
8
- "d_model": 768,
9
- "decoder_start_token_id": 0,
10
- "dropout_rate": 0.1,
11
- "eos_token_id": 1,
12
- "feed_forward_proj": "relu",
13
- "initializer_factor": 1,
14
- "is_encoder_decoder": true,
15
- "layer_norm_epsilon": 0.000001,
16
- "model_type": "t5",
17
- "n_positions": 512,
18
- "num_decoder_layers": 12,
19
- "num_heads": 12,
20
- "num_layers": 12,
21
- "output_past": true,
22
- "pad_token_id": 0,
23
- "relative_attention_num_buckets": 32,
24
- "task_specific_params": {
25
- "summarization": {
26
- "early_stopping": true,
27
- "length_penalty": 2,
28
- "max_length": 200,
29
- "min_length": 30,
30
- "no_repeat_ngram_size": 3,
31
- "num_beams": 4,
32
- "prefix": "summarize: "
33
- },
34
- "translation_en_to_de": {
35
- "early_stopping": true,
36
- "max_length": 300,
37
- "num_beams": 4,
38
- "prefix": "translate English to German: "
39
- },
40
- "translation_en_to_fr": {
41
- "early_stopping": true,
42
- "max_length": 300,
43
- "num_beams": 4,
44
- "prefix": "translate English to French: "
45
- },
46
- "translation_en_to_ro": {
47
- "early_stopping": true,
48
- "max_length": 300,
49
- "num_beams": 4,
50
- "prefix": "translate English to Romanian: "
51
- }
52
  },
53
- "torch_dtype": "float32",
54
- "transformers_version": "4.16.2",
55
- "use_cache": true,
56
- "vocab_size": 32128
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_num_buckets": 32,
24
+ "task_specific_params": {
25
+ "summarization": {
26
+ "early_stopping": true,
27
+ "length_penalty": 2.0,
28
+ "max_length": 200,
29
+ "min_length": 30,
30
+ "no_repeat_ngram_size": 3,
31
+ "num_beams": 4,
32
+ "prefix": "summarize: "
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  },
34
+ "translation_en_to_de": {
35
+ "early_stopping": true,
36
+ "max_length": 300,
37
+ "num_beams": 4,
38
+ "prefix": "translate English to German: "
39
+ },
40
+ "translation_en_to_fr": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to French: "
45
+ },
46
+ "translation_en_to_ro": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to Romanian: "
51
+ }
52
+ },
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.16.2",
55
+ "use_cache": true,
56
+ "vocab_size": 32128
57
+ }