Nellissa commited on
Commit
a421656
·
verified ·
1 Parent(s): 2710eb1

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +44 -19
config.json CHANGED
@@ -1,35 +1,60 @@
1
  {
2
- "_name_or_path": "t5_financial_assistant_improved",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
- "model_type": "t5",
7
- "vocab_size": 32128,
8
- "d_model": 512,
9
  "d_ff": 2048,
10
- "num_layers": 6,
11
- "num_heads": 8,
12
  "d_kv": 64,
 
 
 
13
  "dropout_rate": 0.1,
14
- "layer_norm_epsilon": 1e-06,
15
- "initializer_factor": 1.0,
16
  "feed_forward_proj": "relu",
 
17
  "is_encoder_decoder": true,
18
- "use_cache": true,
 
 
 
 
 
 
 
19
  "pad_token_id": 0,
20
- "eos_token_id": 1,
21
- "decoder_start_token_id": 0,
22
- "model_name": "t5_financial_assistant_improved",
23
  "task_specific_params": {
24
- "text2text-generation": {
25
  "early_stopping": true,
26
- "max_length": 512,
27
- "min_length": 64,
28
- "num_beams": 4,
29
  "length_penalty": 2.0,
 
 
30
  "no_repeat_ngram_size": 3,
31
- "do_sample": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  }
33
  },
34
- "torch_dtype": "float32"
35
- }
 
 
 
1
  {
 
2
  "architectures": [
3
  "T5ForConditionalGeneration"
4
  ],
5
+ "classifier_dropout": 0.0,
 
 
6
  "d_ff": 2048,
 
 
7
  "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
  "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
  "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
  "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
+ "output_past": true,
25
  "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
 
28
  "task_specific_params": {
29
+ "summarization": {
30
  "early_stopping": true,
 
 
 
31
  "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
  "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
  }
56
  },
57
+ "transformers_version": "4.57.1",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }