ybelkada HF staff commited on
Commit
6854668
1 Parent(s): d5e9272

Upload MT5ForConditionalGeneration

Browse files
Files changed (2) hide show
  1. config.json +6 -6
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "hf-internal-testing/tiny-random-mt5",
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,
@@ -17,7 +17,7 @@
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,
@@ -27,5 +27,5 @@
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.25.1",
29
  "use_cache": true,
30
- "vocab_size": 250112
31
  }
 
1
  {
2
+ "_name_or_path": "stas/mt5-tiny-random",
3
  "architectures": [
4
  "MT5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 256,
7
+ "d_kv": 8,
8
+ "d_model": 64,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
 
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "mt5",
19
  "num_decoder_layers": 8,
20
+ "num_heads": 4,
21
  "num_layers": 8,
22
  "pad_token_id": 0,
23
  "relative_attention_max_distance": 128,
 
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.25.1",
29
  "use_cache": true,
30
+ "vocab_size": 5100
31
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b5cfaaea70c0479100da88500fe171ebc9905e4e2e251fdef1432a1f99750e4
3
- size 1200769797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e116c4736d8cfebff79fecd6a86b6d72067d5bfc0e4a26cb3b201340a1979588
3
+ size 6617157