yuewang-sf
commited on
Commit
•
6323d42
1
Parent(s):
1a9f517
Update config.json
Browse files- config.json +5 -13
config.json
CHANGED
@@ -4,35 +4,27 @@
|
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"bos_token_id": 1,
|
7 |
-
"d_ff":
|
8 |
"d_kv": 64,
|
9 |
-
"d_model":
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
12 |
"dropout_rate": 0.1,
|
13 |
"eos_token_id": 2,
|
14 |
"feed_forward_proj": "relu",
|
15 |
-
"gradient_checkpointing": false,
|
16 |
-
"id2label": {
|
17 |
-
"0": "LABEL_0"
|
18 |
-
},
|
19 |
"initializer_factor": 1.0,
|
20 |
"is_encoder_decoder": true,
|
21 |
"is_gated_act": false,
|
22 |
-
"label2id": {
|
23 |
-
"LABEL_0": 0
|
24 |
-
},
|
25 |
"layer_norm_epsilon": 1e-06,
|
26 |
"model_type": "t5",
|
27 |
"n_positions": 512,
|
28 |
-
"num_decoder_layers":
|
29 |
-
"num_heads":
|
30 |
-
"num_layers":
|
31 |
"output_past": true,
|
32 |
"pad_token_id": 0,
|
33 |
"relative_attention_max_distance": 128,
|
34 |
"relative_attention_num_buckets": 32,
|
35 |
-
|
36 |
"torch_dtype": "float16",
|
37 |
"transformers_version": "4.21.3",
|
38 |
"use_cache": true,
|
|
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"bos_token_id": 1,
|
7 |
+
"d_ff": 4096,
|
8 |
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
12 |
"dropout_rate": 0.1,
|
13 |
"eos_token_id": 2,
|
14 |
"feed_forward_proj": "relu",
|
|
|
|
|
|
|
|
|
15 |
"initializer_factor": 1.0,
|
16 |
"is_encoder_decoder": true,
|
17 |
"is_gated_act": false,
|
|
|
|
|
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 24,
|
22 |
+
"num_heads": 16,
|
23 |
+
"num_layers": 24,
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
27 |
"relative_attention_num_buckets": 32,
|
|
|
28 |
"torch_dtype": "float16",
|
29 |
"transformers_version": "4.21.3",
|
30 |
"use_cache": true,
|