Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Instructions to use mariadg/AttackVectorClassifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mariadg/AttackVectorClassifier with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mariadg/AttackVectorClassifier")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("mariadg/AttackVectorClassifier") model = AutoModelForSequenceClassification.from_pretrained("mariadg/AttackVectorClassifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 1
Browse files- config.json +13 -23
- model.safetensors +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +12 -19
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,10 +1,12 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
-
"bos_token_id":
|
| 7 |
-
"
|
|
|
|
| 8 |
"eos_token_id": 2,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
|
@@ -15,33 +17,21 @@
|
|
| 15 |
},
|
| 16 |
"initializer_range": 0.02,
|
| 17 |
"intermediate_size": 3072,
|
|
|
|
| 18 |
"label2id": {
|
| 19 |
"has_framing": 1,
|
| 20 |
"no_framing": 0
|
| 21 |
},
|
| 22 |
-
"layer_norm_eps": 1e-
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"max_relative_positions": -1,
|
| 26 |
-
"model_type": "deberta-v2",
|
| 27 |
-
"norm_rel_ebd": "layer_norm",
|
| 28 |
"num_attention_heads": 12,
|
| 29 |
"num_hidden_layers": 12,
|
| 30 |
-
"pad_token_id":
|
| 31 |
-
"
|
| 32 |
-
"pooler_hidden_act": "gelu",
|
| 33 |
-
"pooler_hidden_size": 768,
|
| 34 |
-
"pos_att_type": [
|
| 35 |
-
"p2c",
|
| 36 |
-
"c2p"
|
| 37 |
-
],
|
| 38 |
-
"position_biased_input": false,
|
| 39 |
-
"position_buckets": 256,
|
| 40 |
-
"relative_attention": true,
|
| 41 |
-
"share_att_key": true,
|
| 42 |
"tie_word_embeddings": true,
|
| 43 |
"transformers_version": "5.13.1",
|
| 44 |
-
"type_vocab_size":
|
| 45 |
"use_cache": false,
|
| 46 |
-
"vocab_size":
|
| 47 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_cross_attention": false,
|
| 3 |
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
"eos_token_id": 2,
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.1,
|
|
|
|
| 17 |
},
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
"intermediate_size": 3072,
|
| 20 |
+
"is_decoder": false,
|
| 21 |
"label2id": {
|
| 22 |
"has_framing": 1,
|
| 23 |
"no_framing": 0
|
| 24 |
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "roberta",
|
|
|
|
|
|
|
|
|
|
| 28 |
"num_attention_heads": 12,
|
| 29 |
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"tie_word_embeddings": true,
|
| 33 |
"transformers_version": "5.13.1",
|
| 34 |
+
"type_vocab_size": 1,
|
| 35 |
"use_cache": false,
|
| 36 |
+
"vocab_size": 50265
|
| 37 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d163027473d6928e116d0910d40d25759d7afb3e2fb3da3bdecf71df0f9e9107
|
| 3 |
+
size 498612824
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,24 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space":
|
| 3 |
"backend": "tokenizers",
|
| 4 |
-
"bos_token": "
|
| 5 |
-
"cls_token": "
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"[PAD]",
|
| 10 |
-
"[CLS]",
|
| 11 |
-
"[SEP]"
|
| 12 |
-
],
|
| 13 |
"is_local": false,
|
| 14 |
"local_files_only": false,
|
| 15 |
-
"mask_token": "
|
| 16 |
-
"model_max_length":
|
| 17 |
-
"pad_token": "
|
| 18 |
-
"sep_token": "
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"unk_token": "[UNK]",
|
| 23 |
-
"vocab_type": "spm"
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"is_local": false,
|
| 9 |
"local_files_only": false,
|
| 10 |
+
"mask_token": "<mask>",
|
| 11 |
+
"model_max_length": 512,
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 15 |
+
"trim_offsets": true,
|
| 16 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
| 17 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fea6b0f9bdf5ea6ac066e8cf19ce0d20cd9e62c216b0b4b928ce53acee686a4a
|
| 3 |
+
size 5201
|