Safetensors
Serbian
t5
procesaur commited on
Commit
1d5bed3
·
verified ·
1 Parent(s): 65ac87a

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +62 -57
  2. generation_config.json +7 -7
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,57 +1,62 @@
1
- {
2
- "architectures": [
3
- "T5ForConditionalGeneration"
4
- ],
5
- "d_ff": 2048,
6
- "d_kv": 64,
7
- "d_model": 768,
8
- "decoder_start_token_id": 0,
9
- "dropout_rate": 0.1,
10
- "eos_token_id": 1,
11
- "feed_forward_proj": "gated-gelu",
12
- "initializer_factor": 1.0,
13
- "is_encoder_decoder": true,
14
- "layer_norm_epsilon": 1e-06,
15
- "model_type": "t5",
16
- "n_positions": 512,
17
- "num_decoder_layers": 12,
18
- "num_heads": 12,
19
- "num_layers": 12,
20
- "output_past": true,
21
- "pad_token_id": 0,
22
- "relative_attention_max_distance": 128,
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
- "tie_word_embeddings": false,
54
- "transformers_version": "4.23.1",
55
- "use_cache": true,
56
- "vocab_size": 32128
57
- }
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "autopiloT5",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 12,
22
+ "num_heads": 12,
23
+ "num_layers": 12,
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
+ "tie_word_embeddings": false,
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.49.0",
60
+ "use_cache": true,
61
+ "vocab_size": 32128
62
+ }
generation_config.json CHANGED
@@ -1,7 +1,7 @@
1
- {
2
- "_from_model_config": true,
3
- "decoder_start_token_id": 0,
4
- "eos_token_id": 1,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.27.0.dev0"
7
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.49.0"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dfb70afdcedceb9f9fae2f9b68e004ad934361fb35b9b2bd50b45ea90790fc8
3
- size 990345061
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46b8052e13cc139cac6e314081da06c77d6373f0282c939390d09cc347c259f
3
+ size 990345064