Voeg auto_map + gekalibreerde null_bias toe voor trust_remote_code
Browse files- config.json +43 -38
config.json
CHANGED
|
@@ -1,38 +1,43 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"DebertaV2ForQuestionAnswering"
|
| 4 |
-
],
|
| 5 |
-
"attention_probs_dropout_prob": 0.1,
|
| 6 |
-
"bos_token_id": 1,
|
| 7 |
-
"dtype": "float32",
|
| 8 |
-
"eos_token_id": 2,
|
| 9 |
-
"hidden_act": "gelu",
|
| 10 |
-
"hidden_dropout_prob": 0.1,
|
| 11 |
-
"hidden_size": 768,
|
| 12 |
-
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size": 3072,
|
| 14 |
-
"layer_norm_eps": 1e-07,
|
| 15 |
-
"legacy": true,
|
| 16 |
-
"max_position_embeddings": 512,
|
| 17 |
-
"max_relative_positions": -1,
|
| 18 |
-
"model_type": "deberta-v2",
|
| 19 |
-
"norm_rel_ebd": "layer_norm",
|
| 20 |
-
"num_attention_heads": 12,
|
| 21 |
-
"num_hidden_layers": 12,
|
| 22 |
-
"pad_token_id": 0,
|
| 23 |
-
"pooler_dropout": 0.0,
|
| 24 |
-
"pooler_hidden_act": "gelu",
|
| 25 |
-
"pooler_hidden_size": 768,
|
| 26 |
-
"pos_att_type": [
|
| 27 |
-
"p2c",
|
| 28 |
-
"c2p"
|
| 29 |
-
],
|
| 30 |
-
"position_biased_input": false,
|
| 31 |
-
"position_buckets": 256,
|
| 32 |
-
"relative_attention": true,
|
| 33 |
-
"share_att_key": true,
|
| 34 |
-
"tie_word_embeddings": true,
|
| 35 |
-
"transformers_version": "5.16.1",
|
| 36 |
-
"type_vocab_size": 0,
|
| 37 |
-
"vocab_size": 251000
|
| 38 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DebertaV2ForQuestionAnswering"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-07,
|
| 15 |
+
"legacy": true,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"max_relative_positions": -1,
|
| 18 |
+
"model_type": "deberta-v2",
|
| 19 |
+
"norm_rel_ebd": "layer_norm",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"pooler_dropout": 0.0,
|
| 24 |
+
"pooler_hidden_act": "gelu",
|
| 25 |
+
"pooler_hidden_size": 768,
|
| 26 |
+
"pos_att_type": [
|
| 27 |
+
"p2c",
|
| 28 |
+
"c2p"
|
| 29 |
+
],
|
| 30 |
+
"position_biased_input": false,
|
| 31 |
+
"position_buckets": 256,
|
| 32 |
+
"relative_attention": true,
|
| 33 |
+
"share_att_key": true,
|
| 34 |
+
"tie_word_embeddings": true,
|
| 35 |
+
"transformers_version": "5.16.1",
|
| 36 |
+
"type_vocab_size": 0,
|
| 37 |
+
"vocab_size": 251000,
|
| 38 |
+
"auto_map": {
|
| 39 |
+
"AutoModel": "modeling_nbclas_qa.NBClasQAModel"
|
| 40 |
+
},
|
| 41 |
+
"null_bias": 4.75,
|
| 42 |
+
"max_answer_length": 30
|
| 43 |
+
}
|