modelo distilbert-base-uncased
Browse files- distilbert/config.json +28 -0
- distilbert/evaluation_results.json +21 -0
- distilbert/model.safetensors +3 -0
- distilbert/tokenizer.json +0 -0
- distilbert/tokenizer_config.json +15 -0
- distilbert/training_args.bin +3 -0
distilbert/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"dtype": "float32",
|
| 11 |
+
"eos_token_id": null,
|
| 12 |
+
"hidden_dim": 3072,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "distilbert",
|
| 16 |
+
"n_heads": 12,
|
| 17 |
+
"n_layers": 6,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"problem_type": "single_label_classification",
|
| 20 |
+
"qa_dropout": 0.1,
|
| 21 |
+
"seq_classif_dropout": 0.2,
|
| 22 |
+
"sinusoidal_pos_embds": false,
|
| 23 |
+
"tie_weights_": true,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"transformers_version": "5.17.0",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 30522
|
| 28 |
+
}
|
distilbert/evaluation_results.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"test": {
|
| 3 |
+
"accuracy": 0.8964923905608755,
|
| 4 |
+
"precision": 0.8571736337234053,
|
| 5 |
+
"recall": 0.8459814150989599,
|
| 6 |
+
"f1": 0.8513647836501375
|
| 7 |
+
},
|
| 8 |
+
"adversarial": {
|
| 9 |
+
"accuracy": 0.9375,
|
| 10 |
+
"precision": 0.9285714285714286,
|
| 11 |
+
"recall": 0.95,
|
| 12 |
+
"f1": 0.9352226720647774,
|
| 13 |
+
"n_examples": 16
|
| 14 |
+
},
|
| 15 |
+
"performance": {
|
| 16 |
+
"device": "cuda",
|
| 17 |
+
"latency_ms_mean": 4.071202001068741,
|
| 18 |
+
"latency_ms_p95": 6.405144993914291,
|
| 19 |
+
"throughput_examples_per_sec": 2562.7759986185893
|
| 20 |
+
}
|
| 21 |
+
}
|
distilbert/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:936f6927b734507ab1726c916a3ff4d43c833c4cb1cf0da1fc5b21179a217f7e
|
| 3 |
+
size 267832560
|
distilbert/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
distilbert/tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"is_local": false,
|
| 6 |
+
"local_files_only": false,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
distilbert/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b620a943f164ed95fcf9d607cddca68e17b7aa51dca4d8cffc6f4ff735fd8c0d
|
| 3 |
+
size 5201
|