HaveAI commited on
Commit
cd7bdcf
·
verified ·
1 Parent(s): 3738334

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +33 -0
  2. generation_config.json +9 -0
  3. merges.txt +0 -0
  4. special_tokens_map.json +19 -5
  5. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ai-forever/sage-fredt5-distilled-95m",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 1024,
9
+ "d_kv": 64,
10
+ "d_model": 512,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "gelu_new",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "gated-gelu",
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "max_length": 256,
21
+ "model_type": "t5",
22
+ "num_decoder_layers": 8,
23
+ "num_heads": 6,
24
+ "num_layers": 8,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "tie_word_embeddings": false,
30
+ "transformers_version": "4.33.2",
31
+ "use_cache": true,
32
+ "vocab_size": 50364
33
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 2,
6
+ "max_length": 256,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.33.2"
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,22 +1,36 @@
1
  {
2
  "bos_token": {
3
- "content": "<|begin▁of▁sentence|>",
4
  "lstrip": false,
5
- "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|end▁of▁sentence|>",
 
 
 
 
 
 
 
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "<|end▁of▁sentence|>",
18
  "lstrip": false,
19
- "normalized": false,
 
 
 
 
 
 
 
20
  "rstrip": false,
21
  "single_word": false
22
  }
 
1
  {
2
  "bos_token": {
3
+ "content": "<LM>",
4
  "lstrip": false,
5
+ "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "pad_token": {
24
+ "content": "<pad>",
25
  "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
  "rstrip": false,
35
  "single_word": false
36
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff