Commit
•
d8e0b80
1
Parent(s):
874c1d9
Delete config.json
Browse files- config.json +0 -33
config.json
DELETED
|
@@ -1,33 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "./best_model",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"MT5ForConditionalGeneration"
|
| 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,
|
| 13 |
-
"eos_token_id": 1,
|
| 14 |
-
"feed_forward_proj": "gated-gelu",
|
| 15 |
-
"initializer_factor": 1.0,
|
| 16 |
-
"is_encoder_decoder": true,
|
| 17 |
-
"is_gated_act": true,
|
| 18 |
-
"layer_norm_epsilon": 1e-06,
|
| 19 |
-
"model_type": "mt5",
|
| 20 |
-
"num_decoder_layers": 12,
|
| 21 |
-
"num_heads": 12,
|
| 22 |
-
"num_layers": 12,
|
| 23 |
-
"output_past": true,
|
| 24 |
-
"pad_token_id": 0,
|
| 25 |
-
"relative_attention_max_distance": 128,
|
| 26 |
-
"relative_attention_num_buckets": 32,
|
| 27 |
-
"tie_word_embeddings": false,
|
| 28 |
-
"tokenizer_class": "T5Tokenizer",
|
| 29 |
-
"torch_dtype": "float32",
|
| 30 |
-
"transformers_version": "4.41.2",
|
| 31 |
-
"use_cache": true,
|
| 32 |
-
"vocab_size": 250112
|
| 33 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|