Hugging Face's logo

tliu
/
asp-re-flan-t5-base

Transformers
PyTorch
Inference Endpoints
Model card Files Community
tliu commited on
Commit
425949e
•
1 Parent(s): c44f5bd

upload

Browse files
Files changed (4) hide show
  1. README.md +0 -3
  2. config.json +67 -0
  3. generation_config.json +67 -0
  4. pytorch_model.bin +3 -0
README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ERE"
4
+ ],
5
+ "asp_activation": "relu",
6
+ "asp_dropout_rate": 0.3,
7
+ "asp_feature_emb_size": 20,
8
+ "asp_hidden_dim": 1500,
9
+ "asp_init_std": 0.02,
10
+ "d_ff": 2048,
11
+ "d_kv": 64,
12
+ "d_model": 768,
13
+ "decoder_start_token_id": 0,
14
+ "dropout_rate": 0.1,
15
+ "eos_token_id": 1,
16
+ "feed_forward_proj": "gated-gelu",
17
+ "initializer_factor": 1.0,
18
+ "is_encoder_decoder": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "mention_end_id": 32101,
21
+ "mention_start_id": 32100,
22
+ "n_positions": 512,
23
+ "num_decoder_layers": 12,
24
+ "num_heads": 12,
25
+ "num_layers": 12,
26
+ "num_linking_classes": 5,
27
+ "num_typing_classes": 4,
28
+ "output_past": true,
29
+ "pad_token_id": 0,
30
+ "pretrained_name_or_path": "google/flan-t5-base",
31
+ "relative_attention_max_distance": 128,
32
+ "relative_attention_num_buckets": 32,
33
+ "task_specific_params": {
34
+ "summarization": {
35
+ "early_stopping": true,
36
+ "length_penalty": 2.0,
37
+ "max_length": 200,
38
+ "min_length": 30,
39
+ "no_repeat_ngram_size": 3,
40
+ "num_beams": 4,
41
+ "prefix": "summarize: "
42
+ },
43
+ "translation_en_to_de": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to German: "
48
+ },
49
+ "translation_en_to_fr": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to French: "
54
+ },
55
+ "translation_en_to_ro": {
56
+ "early_stopping": true,
57
+ "max_length": 300,
58
+ "num_beams": 4,
59
+ "prefix": "translate English to Romanian: "
60
+ }
61
+ },
62
+ "tie_word_embeddings": false,
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.33.3",
65
+ "use_cache": true,
66
+ "vocab_size": 32102
67
+ }
generation_config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ERE"
4
+ ],
5
+ "asp_activation": "relu",
6
+ "asp_dropout_rate": 0.3,
7
+ "asp_feature_emb_size": 20,
8
+ "asp_hidden_dim": 1500,
9
+ "asp_init_std": 0.02,
10
+ "d_ff": 2048,
11
+ "d_kv": 64,
12
+ "d_model": 768,
13
+ "decoder_start_token_id": 0,
14
+ "dropout_rate": 0.1,
15
+ "eos_token_id": 1,
16
+ "feed_forward_proj": "gated-gelu",
17
+ "initializer_factor": 1.0,
18
+ "is_encoder_decoder": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "mention_end_id": 32101,
21
+ "mention_start_id": 32100,
22
+ "n_positions": 512,
23
+ "num_decoder_layers": 12,
24
+ "num_heads": 12,
25
+ "num_layers": 12,
26
+ "num_linking_classes": 5,
27
+ "num_typing_classes": 4,
28
+ "output_past": true,
29
+ "pad_token_id": 0,
30
+ "pretrained_name_or_path": "google/flan-t5-base",
31
+ "relative_attention_max_distance": 128,
32
+ "relative_attention_num_buckets": 32,
33
+ "task_specific_params": {
34
+ "summarization": {
35
+ "early_stopping": true,
36
+ "length_penalty": 2.0,
37
+ "max_length": 200,
38
+ "min_length": 30,
39
+ "no_repeat_ngram_size": 3,
40
+ "num_beams": 4,
41
+ "prefix": "summarize: "
42
+ },
43
+ "translation_en_to_de": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to German: "
48
+ },
49
+ "translation_en_to_fr": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to French: "
54
+ },
55
+ "translation_en_to_ro": {
56
+ "early_stopping": true,
57
+ "max_length": 300,
58
+ "num_beams": 4,
59
+ "prefix": "translate English to Romanian: "
60
+ }
61
+ },
62
+ "tie_word_embeddings": false,
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.33.3",
65
+ "use_cache": true,
66
+ "vocab_size": 32102
67
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd2c9d05cc703f190ac56fe44b30ec92c72ba97eb47b96198ebe6e0c1f2aeca
3
+ size 914790302