whitefoxredhell commited on
Commit
e67ebca
1 Parent(s): 9e07931

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +31 -0
  2. id2label.json +26 -0
  3. special_tokens_map.json +5 -0
  4. tokenizer_config.json +11 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bigscience/mt0-small",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
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": false,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "mt5",
19
+ "num_decoder_layers": 8,
20
+ "num_heads": 6,
21
+ "num_layers": 8,
22
+ "pad_token_id": 0,
23
+ "relative_attention_max_distance": 128,
24
+ "relative_attention_num_buckets": 32,
25
+ "tie_word_embeddings": false,
26
+ "tokenizer_class": "T5Tokenizer",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.30.2",
29
+ "use_cache": false,
30
+ "vocab_size": 250112
31
+ }
id2label.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": "fr",
3
+ "1": "zh",
4
+ "2": "fa",
5
+ "3": "ky",
6
+ "4": "ru",
7
+ "5": "lt",
8
+ "6": "uz",
9
+ "7": "en",
10
+ "8": "pt",
11
+ "9": "bg",
12
+ "10": "th",
13
+ "11": "pl",
14
+ "12": "ur",
15
+ "13": "sw",
16
+ "14": "tr",
17
+ "15": "es",
18
+ "16": "ar",
19
+ "17": "it",
20
+ "18": "hi",
21
+ "19": "de",
22
+ "20": "el",
23
+ "21": "nl",
24
+ "22": "vi",
25
+ "23": "ja"
26
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "extra_ids": 0,
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "tokenizer_class": "T5Tokenizer",
10
+ "unk_token": "<unk>"
11
+ }