AlanRobotics commited on
Commit
d022220
·
1 Parent(s): 216ac5a

Upload T5ForConditionalGeneration

Browse files
Files changed (2) hide show
  1. config.json +39 -10
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,21 +1,23 @@
1
  {
2
- "_name_or_path": "AlanRobotics/ruT5-conversation",
 
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 2048,
7
  "d_kv": 64,
8
  "d_model": 768,
9
  "decoder_start_token_id": 0,
10
- "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
12
- "eos_token_id": 1,
13
- "feed_forward_proj": "gated-gelu",
14
  "initializer_factor": 1.0,
15
  "is_encoder_decoder": true,
16
- "is_gated_act": true,
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
 
19
  "num_decoder_layers": 12,
20
  "num_heads": 12,
21
  "num_layers": 12,
@@ -23,10 +25,37 @@
23
  "pad_token_id": 0,
24
  "relative_attention_max_distance": 128,
25
  "relative_attention_num_buckets": 32,
26
- "tie_word_embeddings": false,
27
- "tokenizer_class": "T5Tokenizer",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  "torch_dtype": "float32",
29
- "transformers_version": "4.24.0",
30
  "use_cache": true,
31
- "vocab_size": 25662
32
  }
 
1
  {
2
+ "_name_or_path": "ai-forever/ruT5-base",
3
+ "_num_labels": 2,
4
  "architectures": [
5
  "T5ForConditionalGeneration"
6
  ],
7
+ "d_ff": 3072,
8
  "d_kv": 64,
9
  "d_model": 768,
10
  "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
  "dropout_rate": 0.1,
13
+ "eos_token_id": 2,
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": 12,
22
  "num_heads": 12,
23
  "num_layers": 12,
 
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
  "torch_dtype": "float32",
58
+ "transformers_version": "4.26.0.dev0",
59
  "use_cache": true,
60
+ "vocab_size": 32128
61
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2fb420242290849521df3339cd7f5a8fb29ea4f4fd6e2173003fda9d98136e5
3
- size 950677813
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfb54e7d70e6e556ab956c9eda563a2506f9f7f7a8dbbb53479d9a7956571a5
3
+ size 891702929