asahi417 commited on
Commit
ac8f724
1 Parent(s): d3aedd2

Upload MT5ForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +52 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ckpts/mt5-small-trimmed-it-10000",
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": true,
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": "4.26.1",
29
+ "use_cache": true,
30
+ "vocab_size": 10001,
31
+ "vocabtrimmer": {
32
+ "mining_config": {
33
+ "dataset": "vocabtrimmer/mc4_validation",
34
+ "dataset_column": "text",
35
+ "dataset_name": "it",
36
+ "dataset_split": "validation",
37
+ "language": "it",
38
+ "min_frequency": 2,
39
+ "target_vocab_size": 10000
40
+ },
41
+ "stats": {
42
+ "compression_rate_embedding": 3.9986086233367453,
43
+ "compression_rate_full": 18.09037533510921,
44
+ "parameter_size_embedding/raw": 256114688,
45
+ "parameter_size_embedding/trimmed": 10241024,
46
+ "parameter_size_full/raw": 300176768,
47
+ "parameter_size_full/trimmed": 54303104,
48
+ "vocab_size/raw": 250112,
49
+ "vocab_size/trimmed": 10001
50
+ }
51
+ }
52
+ }
generation_config.json ADDED
@@ -0,0 +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": "4.26.1"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99bcbd7fb3b48d1ad7695fdc965198f9445fbe083454ce8905ab9dda1143d2d
3
+ size 217275141