Upload 6 files

README.md

@@ -1,3 +1,15 @@
----
-license: apache-2.0
----
+
+# Hacking-Tools Safetensors Dataset
+
+Purpose:
+- Defensive AI training
+- Cybersecurity awareness
+- Threat pattern recognition
+
+Contents:
+- hacking_tools.safetensors : Tokenized dataset
+- config.json : Model configuration
+- tokenizer + vocab files
+
+Warning:
+This dataset is READ-ONLY and must not be used for exploitation.

config.json

@@ -0,0 +1,12 @@
+{
+  "model_type": "bert",
+  "hidden_size": 768,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "max_position_embeddings": 512,
+  "vocab_size": 30522,
+  "architectures": [
+    "BertModel"
+  ],
+  "torch_dtype": "float32"
+}

hacking_tools.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa81f36f1c4f1439bfc1de983460a3656fc1ccde889fe3492eb20ee7c0b5987e
+size 9269416

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "unk_token": "[UNK]",
+  "sep_token": "[SEP]",
+  "pad_token": "[PAD]",
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]"
+}

tokenizer_config.json

@@ -0,0 +1,5 @@
+{
+  "do_lower_case": true,
+  "model_max_length": 512,
+  "tokenizer_class": "BertTokenizerFast"
+}