Serj commited on
Commit
1050308
1 Parent(s): 64f1612

Add Atis dataset sub samples to training dataset

Browse files
Files changed (2) hide show
  1. config.json +6 -6
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "models/flan-t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
- "d_ff": 2048,
8
  "d_kv": 64,
9
- "d_model": 768,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "gelu_new",
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,
 
1
  {
2
+ "_name_or_path": "models/flan-t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 1024,
8
  "d_kv": 64,
9
+ "d_model": 512,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "gelu_new",
12
  "dropout_rate": 0.1,
 
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
+ "num_decoder_layers": 8,
22
+ "num_heads": 6,
23
+ "num_layers": 8,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43dbfad2df7e5942d3bb3f1608099103c64789f4db0518540c63733ce3058e22
3
- size 990345064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed29cb8a3105505cedaea170f0f185a39c7cd5c0066772df26afb98923974542
3
+ size 307867048