patrickvonplaten commited on
Commit
1366423
1 Parent(s): 708c174

Upload model

Browse files
Files changed (2) hide show
  1. README.md +8 -0
  2. config.json +26 -0
README.md ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - t5-new-hf-not-loaded
4
+ ---
5
+
6
+ # Test
7
+ Hf T5:
8
+ MTF T5: -80.44100952148438
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "pad_token_id": 0,
22
+ "relative_attention_num_buckets": 32,
23
+ "transformers_version": "4.17.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32128
26
+ }