pragmaticml commited on
Commit
28fa596
1 Parent(s): 609cef4

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +34 -0
  2. generation_config.json +7 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/byt5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "d_ff": 3584,
8
+ "d_kv": 64,
9
+ "d_model": 1472,
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
+ "gradient_checkpointing": false,
16
+ "hidden_dropout_prob": 0.0,
17
+ "initializer_factor": 1.0,
18
+ "is_encoder_decoder": true,
19
+ "is_gated_act": true,
20
+ "layer_norm_epsilon": 1e-06,
21
+ "model_type": "t5",
22
+ "num_decoder_layers": 4,
23
+ "num_heads": 6,
24
+ "num_layers": 12,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "tokenizer_class": "ByT5Tokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.28.0.dev0",
32
+ "use_cache": true,
33
+ "vocab_size": 384
34
+ }
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": "4.28.0.dev0"
7
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b5027d2d6241297c89faa77f1ded649dd4cfb8a2acce1ee3bd7d07598aae9d
3
+ size 1198609653
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee3dd1e274560f2dda62bcb62fd92ff823b040a8c7686508707299dc7babc591
3
+ size 3579