model update
Browse files- config.json +1 -57
config.json
CHANGED
@@ -1,57 +1 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "t5-large",
|
3 |
-
"architectures": [
|
4 |
-
"T5ForConditionalGeneration"
|
5 |
-
],
|
6 |
-
"d_ff": 4096,
|
7 |
-
"d_kv": 64,
|
8 |
-
"d_model": 1024,
|
9 |
-
"decoder_start_token_id": 0,
|
10 |
-
"dropout_rate": 0.1,
|
11 |
-
"eos_token_id": 1,
|
12 |
-
"feed_forward_proj": "relu",
|
13 |
-
"gradient_checkpointing": false,
|
14 |
-
"initializer_factor": 1.0,
|
15 |
-
"is_encoder_decoder": true,
|
16 |
-
"layer_norm_epsilon": 1e-06,
|
17 |
-
"model_type": "t5",
|
18 |
-
"n_positions": 512,
|
19 |
-
"num_decoder_layers": 24,
|
20 |
-
"num_heads": 16,
|
21 |
-
"num_layers": 24,
|
22 |
-
"output_past": true,
|
23 |
-
"pad_token_id": 0,
|
24 |
-
"relative_attention_num_buckets": 32,
|
25 |
-
"task_specific_params": {
|
26 |
-
"summarization": {
|
27 |
-
"early_stopping": true,
|
28 |
-
"length_penalty": 2.0,
|
29 |
-
"max_length": 200,
|
30 |
-
"min_length": 30,
|
31 |
-
"no_repeat_ngram_size": 3,
|
32 |
-
"num_beams": 4,
|
33 |
-
"prefix": "summarize: "
|
34 |
-
},
|
35 |
-
"translation_en_to_de": {
|
36 |
-
"early_stopping": true,
|
37 |
-
"max_length": 300,
|
38 |
-
"num_beams": 4,
|
39 |
-
"prefix": "translate English to German: "
|
40 |
-
},
|
41 |
-
"translation_en_to_fr": {
|
42 |
-
"early_stopping": true,
|
43 |
-
"max_length": 300,
|
44 |
-
"num_beams": 4,
|
45 |
-
"prefix": "translate English to French: "
|
46 |
-
},
|
47 |
-
"translation_en_to_ro": {
|
48 |
-
"early_stopping": true,
|
49 |
-
"max_length": 300,
|
50 |
-
"num_beams": 4,
|
51 |
-
"prefix": "translate English to Romanian: "
|
52 |
-
}
|
53 |
-
},
|
54 |
-
"transformers_version": "4.8.2",
|
55 |
-
"use_cache": true,
|
56 |
-
"vocab_size": 32101
|
57 |
-
}
|
|
|
1 |
+
{"_name_or_path": "t5-large", "architectures": ["T5ForConditionalGeneration"], "d_ff": 4096, "d_kv": 64, "d_model": 1024, "decoder_start_token_id": 0, "dropout_rate": 0.1, "eos_token_id": 1, "feed_forward_proj": "relu", "gradient_checkpointing": false, "initializer_factor": 1.0, "is_encoder_decoder": true, "layer_norm_epsilon": 1e-06, "model_type": "t5", "n_positions": 512, "num_decoder_layers": 24, "num_heads": 16, "num_layers": 24, "output_past": true, "pad_token_id": 0, "relative_attention_num_buckets": 32, "task_specific_params": {"summarization": {"early_stopping": true, "length_penalty": 2.0, "max_length": 200, "min_length": 30, "no_repeat_ngram_size": 3, "num_beams": 4, "prefix": "summarize: "}, "translation_en_to_de": {"early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to German: "}, "translation_en_to_fr": {"early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to French: "}, "translation_en_to_ro": {"early_stopping": true, "max_length": 300, "num_beams": 4, "prefix": "translate English to Romanian: "}}, "transformers_version": "4.8.2", "use_cache": true, "vocab_size": 32101, "add_prefix": true}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|