Update config.json
Browse files- config.json +5 -14
config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
-
"
|
4 |
],
|
5 |
"d_ff": 2816,
|
6 |
"d_kv": 64,
|
@@ -8,26 +8,17 @@
|
|
8 |
"decoder_start_token_id": 0,
|
9 |
"dropout_rate": 0.1,
|
10 |
"eos_token_id": 1,
|
|
|
11 |
"initializer_factor": 1.0,
|
12 |
"is_encoder_decoder": true,
|
13 |
"layer_norm_epsilon": 1e-06,
|
14 |
"model_type": "t5",
|
15 |
-
"
|
16 |
"num_heads": 16,
|
17 |
"num_layers": 24,
|
18 |
"output_past": true,
|
19 |
"pad_token_id": 0,
|
20 |
"relative_attention_num_buckets": 32,
|
21 |
-
"
|
22 |
-
"summarization": {
|
23 |
-
"early_stopping": true,
|
24 |
-
"length_penalty": 2.0,
|
25 |
-
"max_length": 200,
|
26 |
-
"min_length": 30,
|
27 |
-
"no_repeat_ngram_size": 3,
|
28 |
-
"num_beams": 4,
|
29 |
-
"prefix": "summarize: "
|
30 |
-
}
|
31 |
-
},
|
32 |
"vocab_size": 36000
|
33 |
-
}
|
|
|
1 |
{
|
2 |
"architectures": [
|
3 |
+
"T5ForConditionalGeneration"
|
4 |
],
|
5 |
"d_ff": 2816,
|
6 |
"d_kv": 64,
|
|
|
8 |
"decoder_start_token_id": 0,
|
9 |
"dropout_rate": 0.1,
|
10 |
"eos_token_id": 1,
|
11 |
+
"feed_forward_proj": "gated-gelu",
|
12 |
"initializer_factor": 1.0,
|
13 |
"is_encoder_decoder": true,
|
14 |
"layer_norm_epsilon": 1e-06,
|
15 |
"model_type": "t5",
|
16 |
+
"num_decoder_layers": 24,
|
17 |
"num_heads": 16,
|
18 |
"num_layers": 24,
|
19 |
"output_past": true,
|
20 |
"pad_token_id": 0,
|
21 |
"relative_attention_num_buckets": 32,
|
22 |
+
"tie_word_embeddings": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"vocab_size": 36000
|
24 |
+
}
|