florentianayuwono commited on
Commit
440b47d
1 Parent(s): bf992d3

Upload T5ForConditionalGeneration

Browse files
Files changed (2) hide show
  1. config.json +7 -6
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
- "d_ff": 3072,
8
  "d_kv": 64,
9
- "d_model": 768,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "relu",
12
  "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
- "num_decoder_layers": 12,
22
- "num_heads": 12,
23
- "num_layers": 12,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
@@ -54,6 +54,7 @@
54
  "prefix": "translate English to Romanian: "
55
  }
56
  },
 
57
  "transformers_version": "4.39.3",
58
  "use_cache": true,
59
  "vocab_size": 32101
 
1
  {
2
+ "_name_or_path": "t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
  "d_kv": 64,
9
+ "d_model": 512,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "relu",
12
  "dropout_rate": 0.1,
 
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
 
54
  "prefix": "translate English to Romanian: "
55
  }
56
  },
57
+ "torch_dtype": "float32",
58
  "transformers_version": "4.39.3",
59
  "use_cache": true,
60
  "vocab_size": 32101
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:429a477d70a13884aff463e6167862dd247f0c1346babaadb5d5728b541bd2f9
3
- size 891561768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2234a9a0f359cf17c88e8aa38178d2cfc4035c0184582e38704345f8dfe8f5
3
+ size 241986600