Upload folder using huggingface_hub
Browse files- README.md +17 -17
- classification_head.pth +2 -2
- config.json +359 -217
- merges.txt +0 -0
- model.safetensors +2 -2
- special_tokens_map.json +49 -5
- tokenizer.json +0 -0
- tokenizer_config.json +27 -23
- vocab.json +0 -0
README.md
CHANGED
|
@@ -3,15 +3,16 @@ license: mit
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
tags:
|
| 6 |
-
-
|
| 7 |
-
- vulnerability
|
| 8 |
-
- mitre-attck
|
| 9 |
- text-classification
|
| 10 |
- fine-tuned
|
|
|
|
|
|
|
|
|
|
| 11 |
base_model: ehsanaghaei/SecureBERT
|
| 12 |
---
|
| 13 |
|
| 14 |
-
# SecureBERT — MITRE ATT&CK Classifier
|
| 15 |
|
| 16 |
[](https://theses.fr/s371241)
|
| 17 |
[](https://opensource.org/licenses/MIT)
|
|
@@ -19,7 +20,6 @@ base_model: ehsanaghaei/SecureBERT
|
|
| 19 |
[](https://zenodo.org/records/17368476)
|
| 20 |
[](https://github.com/terranovafr/CVE-LMTune)
|
| 21 |
|
| 22 |
-
|
| 23 |
<div align="center">
|
| 24 |
<img src="https://upload.wikimedia.org/wikipedia/commons/thumb/5/5b/Logo_Universit%C3%A9_de_Lorraine.svg/1280px-Logo_Universit%C3%A9_de_Lorraine.svg.png" alt="Universite de Lorraine" height="50"/>
|
| 25 |
|
|
@@ -41,15 +41,19 @@ Part of the **CVE-LMTune** model suite — language models fine-tuned for multi-
|
|
| 41 |
|
| 42 |
## Task
|
| 43 |
|
| 44 |
-
**MITRE ATT&CK
|
| 45 |
|
| 46 |
-
## Performance
|
| 47 |
|
| 48 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
## Model Structure
|
| 51 |
|
| 52 |
-
|
| 53 |
|
| 54 |
## Quick Start
|
| 55 |
|
|
@@ -57,8 +61,8 @@ flat — standard `AutoModelForSequenceClassification`
|
|
| 57 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 58 |
import torch
|
| 59 |
|
| 60 |
-
tokenizer = AutoTokenizer.from_pretrained("Sana9/securebert-
|
| 61 |
-
model = AutoModelForSequenceClassification.from_pretrained("Sana9/securebert-
|
| 62 |
model.eval()
|
| 63 |
|
| 64 |
text = "Buffer overflow vulnerability in OpenSSL allows remote attackers to execute arbitrary code."
|
|
@@ -66,12 +70,9 @@ inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
|
|
| 66 |
|
| 67 |
with torch.no_grad():
|
| 68 |
logits = model(**inputs).logits
|
| 69 |
-
probs = torch.sigmoid(logits) # multi-label
|
| 70 |
```
|
| 71 |
|
| 72 |
-
> **Note for hierarchical models:** This repo contains multiple sub-folders (master + slave models).
|
| 73 |
-
> Load each sub-folder separately using `from_pretrained("Sana9/securebert-mitre-attack/master")` etc.
|
| 74 |
-
|
| 75 |
## Citation
|
| 76 |
|
| 77 |
```bibtex
|
|
@@ -90,9 +91,8 @@ with torch.no_grad():
|
|
| 90 |
- 📦 [Zenodo — Data repository](https://doi.org/10.5281/zenodo.16936476)
|
| 91 |
- 📦 [Zenodo — Code repository](https://zenodo.org/records/17368476)
|
| 92 |
|
| 93 |
-
|
| 94 |
## Disclaimers
|
| 95 |
|
| 96 |
- This product uses the NVD API but is not endorsed or certified by the NVD.
|
| 97 |
- This project relies on data publicly available from the CWE, CAPEC, and MITRE ATT&CK projects.
|
| 98 |
-
- This work has been partially supported by the French National Research Agency under the France 2030 label (Superviz ANR-22-PECY-0008).
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
tags:
|
| 6 |
+
- mitre-attack
|
|
|
|
|
|
|
| 7 |
- text-classification
|
| 8 |
- fine-tuned
|
| 9 |
+
- cybersecurity
|
| 10 |
+
- vulnerability
|
| 11 |
+
- securebert
|
| 12 |
base_model: ehsanaghaei/SecureBERT
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# SecureBERT — MITRE ATT&CK Enterprise Subtechniques Flat Classifier
|
| 16 |
|
| 17 |
[](https://theses.fr/s371241)
|
| 18 |
[](https://opensource.org/licenses/MIT)
|
|
|
|
| 20 |
[](https://zenodo.org/records/17368476)
|
| 21 |
[](https://github.com/terranovafr/CVE-LMTune)
|
| 22 |
|
|
|
|
| 23 |
<div align="center">
|
| 24 |
<img src="https://upload.wikimedia.org/wikipedia/commons/thumb/5/5b/Logo_Universit%C3%A9_de_Lorraine.svg/1280px-Logo_Universit%C3%A9_de_Lorraine.svg.png" alt="Universite de Lorraine" height="50"/>
|
| 25 |
|
|
|
|
| 41 |
|
| 42 |
## Task
|
| 43 |
|
| 44 |
+
**MITRE ATT&CK Enterprise Subtechniques flat multi-label classification**
|
| 45 |
|
| 46 |
+
## Performance (test set)
|
| 47 |
|
| 48 |
+
| Metric | Score |
|
| 49 |
+
|---|---|
|
| 50 |
+
| Micro-F1 | **0.8168** |
|
| 51 |
+
| LRAP | **0.9152** |
|
| 52 |
+
| Mean Reciprocal Rank | **0.9460** |
|
| 53 |
|
| 54 |
## Model Structure
|
| 55 |
|
| 56 |
+
Flat classifier (single model, multi-label output via sigmoid).
|
| 57 |
|
| 58 |
## Quick Start
|
| 59 |
|
|
|
|
| 61 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 62 |
import torch
|
| 63 |
|
| 64 |
+
tokenizer = AutoTokenizer.from_pretrained("Sana9/securebert-vuln2attack-flat")
|
| 65 |
+
model = AutoModelForSequenceClassification.from_pretrained("Sana9/securebert-vuln2attack-flat")
|
| 66 |
model.eval()
|
| 67 |
|
| 68 |
text = "Buffer overflow vulnerability in OpenSSL allows remote attackers to execute arbitrary code."
|
|
|
|
| 70 |
|
| 71 |
with torch.no_grad():
|
| 72 |
logits = model(**inputs).logits
|
| 73 |
+
probs = torch.sigmoid(logits) # multi-label -> sigmoid
|
| 74 |
```
|
| 75 |
|
|
|
|
|
|
|
|
|
|
| 76 |
## Citation
|
| 77 |
|
| 78 |
```bibtex
|
|
|
|
| 91 |
- 📦 [Zenodo — Data repository](https://doi.org/10.5281/zenodo.16936476)
|
| 92 |
- 📦 [Zenodo — Code repository](https://zenodo.org/records/17368476)
|
| 93 |
|
|
|
|
| 94 |
## Disclaimers
|
| 95 |
|
| 96 |
- This product uses the NVD API but is not endorsed or certified by the NVD.
|
| 97 |
- This project relies on data publicly available from the CWE, CAPEC, and MITRE ATT&CK projects.
|
| 98 |
+
- This work has been partially supported by the French National Research Agency under the France 2030 label (Superviz ANR-22-PECY-0008).
|
classification_head.pth
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:dbff92443b037fb7b395643e9e94de0ba333ee7effd249d166b1be418d3f9b57
|
| 3 |
+
size 2902896
|
config.json
CHANGED
|
@@ -1,240 +1,382 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 6 |
"classifier_dropout": 0,
|
|
|
|
| 7 |
"gradient_checkpointing": false,
|
| 8 |
"hidden_act": "gelu",
|
| 9 |
"hidden_dropout_prob": 0,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"id2label": {
|
| 12 |
-
"0": "
|
| 13 |
-
"1": "
|
| 14 |
-
"2": "
|
| 15 |
-
"3": "
|
| 16 |
-
"4": "
|
| 17 |
-
"5": "
|
| 18 |
-
"6": "T1574.
|
| 19 |
-
"7": "
|
| 20 |
-
"8": "
|
| 21 |
-
"9": "
|
| 22 |
-
"10": "
|
| 23 |
-
"11": "
|
| 24 |
-
"12": "
|
| 25 |
-
"13": "
|
| 26 |
-
"14": "
|
| 27 |
-
"15": "
|
| 28 |
-
"16": "
|
| 29 |
-
"17": "
|
| 30 |
-
"18": "
|
| 31 |
-
"19": "
|
| 32 |
-
"20": "
|
| 33 |
-
"21": "
|
| 34 |
-
"22": "
|
| 35 |
-
"23": "
|
| 36 |
-
"24": "
|
| 37 |
-
"25": "
|
| 38 |
-
"26": "
|
| 39 |
-
"27": "
|
| 40 |
-
"28": "
|
| 41 |
-
"29": "
|
| 42 |
-
"30": "
|
| 43 |
-
"31": "
|
| 44 |
-
"32": "
|
| 45 |
-
"33": "
|
| 46 |
-
"34": "
|
| 47 |
-
"35": "
|
| 48 |
-
"36": "
|
| 49 |
-
"37": "
|
| 50 |
-
"38": "
|
| 51 |
-
"39": "
|
| 52 |
-
"40": "T1562.
|
| 53 |
-
"41": "T1110.
|
| 54 |
-
"42": "
|
| 55 |
-
"43": "
|
| 56 |
-
"44": "
|
| 57 |
-
"45": "
|
| 58 |
-
"46": "
|
| 59 |
-
"47": "
|
| 60 |
-
"48": "
|
| 61 |
-
"49": "
|
| 62 |
-
"50": "
|
| 63 |
-
"51": "
|
| 64 |
-
"52": "
|
| 65 |
-
"53": "
|
| 66 |
-
"54": "
|
| 67 |
-
"55": "
|
| 68 |
-
"56": "
|
| 69 |
-
"57": "
|
| 70 |
-
"58": "
|
| 71 |
-
"59": "
|
| 72 |
-
"60": "
|
| 73 |
-
"61": "
|
| 74 |
-
"62": "
|
| 75 |
-
"63": "
|
| 76 |
-
"64": "
|
| 77 |
-
"65": "
|
| 78 |
-
"66": "
|
| 79 |
-
"67": "
|
| 80 |
-
"68": "
|
| 81 |
-
"69": "
|
| 82 |
-
"70": "
|
| 83 |
-
"71": "
|
| 84 |
-
"72": "
|
| 85 |
-
"73": "
|
| 86 |
-
"74": "
|
| 87 |
-
"75": "
|
| 88 |
-
"76": "
|
| 89 |
-
"77": "
|
| 90 |
-
"78": "
|
| 91 |
-
"79": "
|
| 92 |
-
"80": "
|
| 93 |
-
"81": "
|
| 94 |
-
"82": "
|
| 95 |
-
"83": "
|
| 96 |
-
"84": "
|
| 97 |
-
"85": "
|
| 98 |
-
"86": "
|
| 99 |
-
"87": "
|
| 100 |
-
"88": "
|
| 101 |
-
"89": "
|
| 102 |
-
"90": "
|
| 103 |
-
"91": "
|
| 104 |
-
"92": "
|
| 105 |
-
"93": "
|
| 106 |
-
"94": "
|
| 107 |
-
"95": "
|
| 108 |
-
"96": "
|
| 109 |
-
"97": "
|
| 110 |
-
"98": "
|
| 111 |
-
"99": "
|
| 112 |
-
"100": "
|
| 113 |
-
"101": "
|
| 114 |
-
"102": "
|
| 115 |
-
"103": "
|
| 116 |
-
"104": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
},
|
| 118 |
"initializer_range": 0.02,
|
| 119 |
"intermediate_size": 3072,
|
| 120 |
"label2id": {
|
| 121 |
-
"
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
-
"
|
| 125 |
-
"
|
| 126 |
-
"
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
-
"
|
| 131 |
-
"T1027
|
| 132 |
-
"
|
| 133 |
-
"
|
| 134 |
-
"
|
| 135 |
-
"
|
| 136 |
-
"
|
| 137 |
-
"
|
| 138 |
-
"
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
"
|
| 142 |
-
"
|
| 143 |
-
"
|
| 144 |
-
"
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"
|
| 148 |
-
"
|
| 149 |
-
"
|
| 150 |
-
"
|
| 151 |
-
"
|
| 152 |
-
"
|
| 153 |
-
"
|
| 154 |
-
"
|
| 155 |
-
"
|
| 156 |
-
"
|
| 157 |
-
"
|
| 158 |
-
"
|
| 159 |
-
"
|
| 160 |
-
"
|
| 161 |
-
"
|
| 162 |
-
"
|
| 163 |
-
"
|
| 164 |
-
"
|
| 165 |
-
"
|
| 166 |
-
"
|
| 167 |
-
"
|
| 168 |
-
"
|
| 169 |
-
"
|
| 170 |
-
"
|
| 171 |
-
"
|
| 172 |
-
"
|
| 173 |
-
"
|
| 174 |
-
"
|
| 175 |
-
"
|
| 176 |
-
"
|
| 177 |
-
"
|
| 178 |
-
"
|
| 179 |
-
"
|
| 180 |
-
"
|
| 181 |
-
"
|
| 182 |
-
"
|
| 183 |
-
"
|
| 184 |
-
"
|
| 185 |
-
"
|
| 186 |
-
"
|
| 187 |
-
"
|
| 188 |
-
"
|
| 189 |
-
"
|
| 190 |
-
"
|
| 191 |
-
"
|
| 192 |
-
"
|
| 193 |
-
"
|
| 194 |
-
"
|
| 195 |
-
"
|
| 196 |
-
"
|
| 197 |
-
"
|
| 198 |
-
"
|
| 199 |
-
"
|
| 200 |
-
"
|
| 201 |
-
"
|
| 202 |
-
"
|
| 203 |
-
"
|
| 204 |
-
"
|
| 205 |
-
"
|
| 206 |
-
"
|
| 207 |
-
"
|
| 208 |
-
"
|
| 209 |
-
"
|
| 210 |
-
"
|
| 211 |
-
"
|
| 212 |
-
"
|
| 213 |
-
"
|
| 214 |
-
"
|
| 215 |
-
"
|
| 216 |
-
"
|
| 217 |
-
"
|
| 218 |
-
"
|
| 219 |
-
"
|
| 220 |
-
"
|
| 221 |
-
"
|
| 222 |
-
"
|
| 223 |
-
"
|
| 224 |
-
"
|
| 225 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 226 |
},
|
| 227 |
-
"layer_norm_eps": 1e-
|
| 228 |
-
"max_position_embeddings":
|
| 229 |
-
"model_type": "
|
| 230 |
"num_attention_heads": 12,
|
| 231 |
"num_hidden_layers": 12,
|
| 232 |
-
"pad_token_id":
|
| 233 |
"position_embedding_type": "absolute",
|
| 234 |
"problem_type": "multi_label_classification",
|
| 235 |
"torch_dtype": "float32",
|
| 236 |
"transformers_version": "4.51.3",
|
| 237 |
-
"type_vocab_size":
|
| 238 |
"use_cache": true,
|
| 239 |
-
"vocab_size":
|
| 240 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"RobertaForSequenceClassification"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
"classifier_dropout": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
"gradient_checkpointing": false,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0,
|
| 12 |
"hidden_size": 768,
|
| 13 |
"id2label": {
|
| 14 |
+
"0": "T1195",
|
| 15 |
+
"1": "T1115",
|
| 16 |
+
"2": "T1600",
|
| 17 |
+
"3": "T1543.001",
|
| 18 |
+
"4": "T1090.001",
|
| 19 |
+
"5": "T1592.002",
|
| 20 |
+
"6": "T1574.011",
|
| 21 |
+
"7": "T1110",
|
| 22 |
+
"8": "T1558.003",
|
| 23 |
+
"9": "T1027",
|
| 24 |
+
"10": "T1592",
|
| 25 |
+
"11": "T1134.002",
|
| 26 |
+
"12": "T1553.002",
|
| 27 |
+
"13": "T1110.004",
|
| 28 |
+
"14": "T1611",
|
| 29 |
+
"15": "T1562.009",
|
| 30 |
+
"16": "T1550.001",
|
| 31 |
+
"17": "T1574.004",
|
| 32 |
+
"18": "T1562.004",
|
| 33 |
+
"19": "T1033",
|
| 34 |
+
"20": "T1531",
|
| 35 |
+
"21": "T1564.009",
|
| 36 |
+
"22": "T1498.001",
|
| 37 |
+
"23": "T1595",
|
| 38 |
+
"24": "T1574.008",
|
| 39 |
+
"25": "T1016",
|
| 40 |
+
"26": "T1039",
|
| 41 |
+
"27": "T1110.003",
|
| 42 |
+
"28": "T1620",
|
| 43 |
+
"29": "T1027.003",
|
| 44 |
+
"30": "T1513",
|
| 45 |
+
"31": "T1574.010",
|
| 46 |
+
"32": "T1546.001",
|
| 47 |
+
"33": "T1566.003",
|
| 48 |
+
"34": "T1574.013",
|
| 49 |
+
"35": "T1491",
|
| 50 |
+
"36": "T1120",
|
| 51 |
+
"37": "T1552.001",
|
| 52 |
+
"38": "T1562.002",
|
| 53 |
+
"39": "T1055.003",
|
| 54 |
+
"40": "T1562.008",
|
| 55 |
+
"41": "T1110.002",
|
| 56 |
+
"42": "T1046",
|
| 57 |
+
"43": "T1615",
|
| 58 |
+
"44": "T1562.007",
|
| 59 |
+
"45": "T1557",
|
| 60 |
+
"46": "T1562.001",
|
| 61 |
+
"47": "T1012",
|
| 62 |
+
"48": "T1049",
|
| 63 |
+
"49": "T1557.002",
|
| 64 |
+
"50": "T1546.004",
|
| 65 |
+
"51": "T1211",
|
| 66 |
+
"52": "T1036.001",
|
| 67 |
+
"53": "T1134.003",
|
| 68 |
+
"54": "T1195.001",
|
| 69 |
+
"55": "T1072",
|
| 70 |
+
"56": "T1005",
|
| 71 |
+
"57": "T1001.002",
|
| 72 |
+
"58": "T1119",
|
| 73 |
+
"59": "T1574.007",
|
| 74 |
+
"60": "T1092",
|
| 75 |
+
"61": "T1566.001",
|
| 76 |
+
"62": "T1114.002",
|
| 77 |
+
"63": "T1055",
|
| 78 |
+
"64": "T1213",
|
| 79 |
+
"65": "T1217",
|
| 80 |
+
"66": "T1547.004",
|
| 81 |
+
"67": "T1113",
|
| 82 |
+
"68": "T1550.003",
|
| 83 |
+
"69": "T1574.006",
|
| 84 |
+
"70": "T1135",
|
| 85 |
+
"71": "T1499.001",
|
| 86 |
+
"72": "T1003",
|
| 87 |
+
"73": "T1027.004",
|
| 88 |
+
"74": "T1566.002",
|
| 89 |
+
"75": "T1087",
|
| 90 |
+
"76": "T1550.004",
|
| 91 |
+
"77": "T1056.004",
|
| 92 |
+
"78": "T1534",
|
| 93 |
+
"79": "T1090.004",
|
| 94 |
+
"80": "T1547.001",
|
| 95 |
+
"81": "T1552.006",
|
| 96 |
+
"82": "T1574.001",
|
| 97 |
+
"83": "T1547.014",
|
| 98 |
+
"84": "T1082",
|
| 99 |
+
"85": "T1574.002",
|
| 100 |
+
"86": "T1606.001",
|
| 101 |
+
"87": "T1557.003",
|
| 102 |
+
"88": "T1555.001",
|
| 103 |
+
"89": "T1021.002",
|
| 104 |
+
"90": "T1647",
|
| 105 |
+
"91": "T1185",
|
| 106 |
+
"92": "T1069",
|
| 107 |
+
"93": "T1553.004",
|
| 108 |
+
"94": "T1083",
|
| 109 |
+
"95": "T1021",
|
| 110 |
+
"96": "T1550.002",
|
| 111 |
+
"97": "T1027.009",
|
| 112 |
+
"98": "T1080",
|
| 113 |
+
"99": "T1111",
|
| 114 |
+
"100": "T1123",
|
| 115 |
+
"101": "T1542.002",
|
| 116 |
+
"102": "T1539",
|
| 117 |
+
"103": "T1195.002",
|
| 118 |
+
"104": "T1543.003",
|
| 119 |
+
"105": "T1555",
|
| 120 |
+
"106": "T1598.003",
|
| 121 |
+
"107": "T1547.006",
|
| 122 |
+
"108": "T1543",
|
| 123 |
+
"109": "T1110.001",
|
| 124 |
+
"110": "T1543.004",
|
| 125 |
+
"111": "T1499.002",
|
| 126 |
+
"112": "T1562.003",
|
| 127 |
+
"113": "T1558",
|
| 128 |
+
"114": "T1134.001",
|
| 129 |
+
"115": "T1134",
|
| 130 |
+
"116": "T1499.004",
|
| 131 |
+
"117": "T1598.002",
|
| 132 |
+
"118": "T1498.002",
|
| 133 |
+
"119": "T1552.004",
|
| 134 |
+
"120": "T1546.008",
|
| 135 |
+
"121": "T1548",
|
| 136 |
+
"122": "T1027.006",
|
| 137 |
+
"123": "T1078",
|
| 138 |
+
"124": "T1036.006",
|
| 139 |
+
"125": "T1584.002",
|
| 140 |
+
"126": "T1554",
|
| 141 |
+
"127": "T1007",
|
| 142 |
+
"128": "T1556.006",
|
| 143 |
+
"129": "T1556",
|
| 144 |
+
"130": "T1548.004",
|
| 145 |
+
"131": "T1036.007",
|
| 146 |
+
"132": "T1056",
|
| 147 |
+
"133": "T1614",
|
| 148 |
+
"134": "T1552.002",
|
| 149 |
+
"135": "T1542.003",
|
| 150 |
+
"136": "T1563",
|
| 151 |
+
"137": "T1546.016",
|
| 152 |
+
"138": "T1530",
|
| 153 |
+
"139": "T1078.001",
|
| 154 |
+
"140": "T1057",
|
| 155 |
+
"141": "T1547",
|
| 156 |
+
"142": "T1040",
|
| 157 |
+
"143": "T1037",
|
| 158 |
+
"144": "T1602",
|
| 159 |
+
"145": "T1606",
|
| 160 |
+
"146": "T1598",
|
| 161 |
+
"147": "T1574.009",
|
| 162 |
+
"148": "T1528",
|
| 163 |
+
"149": "T1133",
|
| 164 |
+
"150": "T1505.004",
|
| 165 |
+
"151": "T1176",
|
| 166 |
+
"152": "T1036",
|
| 167 |
+
"153": "T1505.003",
|
| 168 |
+
"154": "T1125",
|
| 169 |
+
"155": "T1221",
|
| 170 |
+
"156": "T1598.001",
|
| 171 |
+
"157": "T1036.005",
|
| 172 |
+
"158": "T1574.005",
|
| 173 |
+
"159": "T1547.009",
|
| 174 |
+
"160": "T1218.001",
|
| 175 |
+
"161": "T1566",
|
| 176 |
+
"162": "T1499",
|
| 177 |
+
"163": "T1112",
|
| 178 |
+
"164": "T1499.003",
|
| 179 |
+
"165": "T1018",
|
| 180 |
+
"166": "T1014",
|
| 181 |
+
"167": "T1036.004",
|
| 182 |
+
"168": "T1070",
|
| 183 |
+
"169": "T1505.005",
|
| 184 |
+
"170": "T1091",
|
| 185 |
+
"171": "T1590",
|
| 186 |
+
"172": "T1552.003",
|
| 187 |
+
"173": "T1124",
|
| 188 |
+
"174": "T1565.002"
|
| 189 |
},
|
| 190 |
"initializer_range": 0.02,
|
| 191 |
"intermediate_size": 3072,
|
| 192 |
"label2id": {
|
| 193 |
+
"T1001.002": 57,
|
| 194 |
+
"T1003": 72,
|
| 195 |
+
"T1005": 56,
|
| 196 |
+
"T1007": 127,
|
| 197 |
+
"T1012": 47,
|
| 198 |
+
"T1014": 166,
|
| 199 |
+
"T1016": 25,
|
| 200 |
+
"T1018": 165,
|
| 201 |
+
"T1021": 95,
|
| 202 |
+
"T1021.002": 89,
|
| 203 |
+
"T1027": 9,
|
| 204 |
+
"T1027.003": 29,
|
| 205 |
+
"T1027.004": 73,
|
| 206 |
+
"T1027.006": 122,
|
| 207 |
+
"T1027.009": 97,
|
| 208 |
+
"T1033": 19,
|
| 209 |
+
"T1036": 152,
|
| 210 |
+
"T1036.001": 52,
|
| 211 |
+
"T1036.004": 167,
|
| 212 |
+
"T1036.005": 157,
|
| 213 |
+
"T1036.006": 124,
|
| 214 |
+
"T1036.007": 131,
|
| 215 |
+
"T1037": 143,
|
| 216 |
+
"T1039": 26,
|
| 217 |
+
"T1040": 142,
|
| 218 |
+
"T1046": 42,
|
| 219 |
+
"T1049": 48,
|
| 220 |
+
"T1055": 63,
|
| 221 |
+
"T1055.003": 39,
|
| 222 |
+
"T1056": 132,
|
| 223 |
+
"T1056.004": 77,
|
| 224 |
+
"T1057": 140,
|
| 225 |
+
"T1069": 92,
|
| 226 |
+
"T1070": 168,
|
| 227 |
+
"T1072": 55,
|
| 228 |
+
"T1078": 123,
|
| 229 |
+
"T1078.001": 139,
|
| 230 |
+
"T1080": 98,
|
| 231 |
+
"T1082": 84,
|
| 232 |
+
"T1083": 94,
|
| 233 |
+
"T1087": 75,
|
| 234 |
+
"T1090.001": 4,
|
| 235 |
+
"T1090.004": 79,
|
| 236 |
+
"T1091": 170,
|
| 237 |
+
"T1092": 60,
|
| 238 |
+
"T1110": 7,
|
| 239 |
+
"T1110.001": 109,
|
| 240 |
+
"T1110.002": 41,
|
| 241 |
+
"T1110.003": 27,
|
| 242 |
+
"T1110.004": 13,
|
| 243 |
+
"T1111": 99,
|
| 244 |
+
"T1112": 163,
|
| 245 |
+
"T1113": 67,
|
| 246 |
+
"T1114.002": 62,
|
| 247 |
+
"T1115": 1,
|
| 248 |
+
"T1119": 58,
|
| 249 |
+
"T1120": 36,
|
| 250 |
+
"T1123": 100,
|
| 251 |
+
"T1124": 173,
|
| 252 |
+
"T1125": 154,
|
| 253 |
+
"T1133": 149,
|
| 254 |
+
"T1134": 115,
|
| 255 |
+
"T1134.001": 114,
|
| 256 |
+
"T1134.002": 11,
|
| 257 |
+
"T1134.003": 53,
|
| 258 |
+
"T1135": 70,
|
| 259 |
+
"T1176": 151,
|
| 260 |
+
"T1185": 91,
|
| 261 |
+
"T1195": 0,
|
| 262 |
+
"T1195.001": 54,
|
| 263 |
+
"T1195.002": 103,
|
| 264 |
+
"T1211": 51,
|
| 265 |
+
"T1213": 64,
|
| 266 |
+
"T1217": 65,
|
| 267 |
+
"T1218.001": 160,
|
| 268 |
+
"T1221": 155,
|
| 269 |
+
"T1491": 35,
|
| 270 |
+
"T1498.001": 22,
|
| 271 |
+
"T1498.002": 118,
|
| 272 |
+
"T1499": 162,
|
| 273 |
+
"T1499.001": 71,
|
| 274 |
+
"T1499.002": 111,
|
| 275 |
+
"T1499.003": 164,
|
| 276 |
+
"T1499.004": 116,
|
| 277 |
+
"T1505.003": 153,
|
| 278 |
+
"T1505.004": 150,
|
| 279 |
+
"T1505.005": 169,
|
| 280 |
+
"T1513": 30,
|
| 281 |
+
"T1528": 148,
|
| 282 |
+
"T1530": 138,
|
| 283 |
+
"T1531": 20,
|
| 284 |
+
"T1534": 78,
|
| 285 |
+
"T1539": 102,
|
| 286 |
+
"T1542.002": 101,
|
| 287 |
+
"T1542.003": 135,
|
| 288 |
+
"T1543": 108,
|
| 289 |
+
"T1543.001": 3,
|
| 290 |
+
"T1543.003": 104,
|
| 291 |
+
"T1543.004": 110,
|
| 292 |
+
"T1546.001": 32,
|
| 293 |
+
"T1546.004": 50,
|
| 294 |
+
"T1546.008": 120,
|
| 295 |
+
"T1546.016": 137,
|
| 296 |
+
"T1547": 141,
|
| 297 |
+
"T1547.001": 80,
|
| 298 |
+
"T1547.004": 66,
|
| 299 |
+
"T1547.006": 107,
|
| 300 |
+
"T1547.009": 159,
|
| 301 |
+
"T1547.014": 83,
|
| 302 |
+
"T1548": 121,
|
| 303 |
+
"T1548.004": 130,
|
| 304 |
+
"T1550.001": 16,
|
| 305 |
+
"T1550.002": 96,
|
| 306 |
+
"T1550.003": 68,
|
| 307 |
+
"T1550.004": 76,
|
| 308 |
+
"T1552.001": 37,
|
| 309 |
+
"T1552.002": 134,
|
| 310 |
+
"T1552.003": 172,
|
| 311 |
+
"T1552.004": 119,
|
| 312 |
+
"T1552.006": 81,
|
| 313 |
+
"T1553.002": 12,
|
| 314 |
+
"T1553.004": 93,
|
| 315 |
+
"T1554": 126,
|
| 316 |
+
"T1555": 105,
|
| 317 |
+
"T1555.001": 88,
|
| 318 |
+
"T1556": 129,
|
| 319 |
+
"T1556.006": 128,
|
| 320 |
+
"T1557": 45,
|
| 321 |
+
"T1557.002": 49,
|
| 322 |
+
"T1557.003": 87,
|
| 323 |
+
"T1558": 113,
|
| 324 |
+
"T1558.003": 8,
|
| 325 |
+
"T1562.001": 46,
|
| 326 |
+
"T1562.002": 38,
|
| 327 |
+
"T1562.003": 112,
|
| 328 |
+
"T1562.004": 18,
|
| 329 |
+
"T1562.007": 44,
|
| 330 |
+
"T1562.008": 40,
|
| 331 |
+
"T1562.009": 15,
|
| 332 |
+
"T1563": 136,
|
| 333 |
+
"T1564.009": 21,
|
| 334 |
+
"T1565.002": 174,
|
| 335 |
+
"T1566": 161,
|
| 336 |
+
"T1566.001": 61,
|
| 337 |
+
"T1566.002": 74,
|
| 338 |
+
"T1566.003": 33,
|
| 339 |
+
"T1574.001": 82,
|
| 340 |
+
"T1574.002": 85,
|
| 341 |
+
"T1574.004": 17,
|
| 342 |
+
"T1574.005": 158,
|
| 343 |
+
"T1574.006": 69,
|
| 344 |
+
"T1574.007": 59,
|
| 345 |
+
"T1574.008": 24,
|
| 346 |
+
"T1574.009": 147,
|
| 347 |
+
"T1574.010": 31,
|
| 348 |
+
"T1574.011": 6,
|
| 349 |
+
"T1574.013": 34,
|
| 350 |
+
"T1584.002": 125,
|
| 351 |
+
"T1590": 171,
|
| 352 |
+
"T1592": 10,
|
| 353 |
+
"T1592.002": 5,
|
| 354 |
+
"T1595": 23,
|
| 355 |
+
"T1598": 146,
|
| 356 |
+
"T1598.001": 156,
|
| 357 |
+
"T1598.002": 117,
|
| 358 |
+
"T1598.003": 106,
|
| 359 |
+
"T1600": 2,
|
| 360 |
+
"T1602": 144,
|
| 361 |
+
"T1606": 145,
|
| 362 |
+
"T1606.001": 86,
|
| 363 |
+
"T1611": 14,
|
| 364 |
+
"T1614": 133,
|
| 365 |
+
"T1615": 43,
|
| 366 |
+
"T1620": 28,
|
| 367 |
+
"T1647": 90
|
| 368 |
},
|
| 369 |
+
"layer_norm_eps": 1e-05,
|
| 370 |
+
"max_position_embeddings": 514,
|
| 371 |
+
"model_type": "roberta",
|
| 372 |
"num_attention_heads": 12,
|
| 373 |
"num_hidden_layers": 12,
|
| 374 |
+
"pad_token_id": 1,
|
| 375 |
"position_embedding_type": "absolute",
|
| 376 |
"problem_type": "multi_label_classification",
|
| 377 |
"torch_dtype": "float32",
|
| 378 |
"transformers_version": "4.51.3",
|
| 379 |
+
"type_vocab_size": 1,
|
| 380 |
"use_cache": true,
|
| 381 |
+
"vocab_size": 50265
|
| 382 |
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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 sha256:07ee5678fd94ce214419121560219ace9b182137b13ea1209508de7ee056cd9c
|
| 3 |
+
size 499144972
|
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,51 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,56 +1,60 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "
|
| 5 |
"lstrip": false,
|
| 6 |
-
"normalized":
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
-
"content": "
|
| 13 |
"lstrip": false,
|
| 14 |
-
"normalized":
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
-
"content": "
|
| 21 |
"lstrip": false,
|
| 22 |
-
"normalized":
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
-
"content": "
|
| 29 |
"lstrip": false,
|
| 30 |
-
"normalized":
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
-
"content": "
|
| 37 |
-
"lstrip":
|
| 38 |
-
"normalized":
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": false,
|
| 45 |
-
"cls_token": "
|
| 46 |
"do_lower_case": true,
|
|
|
|
|
|
|
| 47 |
"extra_special_tokens": {},
|
| 48 |
-
"mask_token": "
|
|
|
|
| 49 |
"model_max_length": 512,
|
| 50 |
-
"pad_token": "
|
| 51 |
-
"sep_token": "
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"unk_token": "[UNK]"
|
| 56 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
| 19 |
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
| 27 |
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false,
|
| 34 |
"special": true
|
| 35 |
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
"rstrip": false,
|
| 41 |
"single_word": false,
|
| 42 |
"special": true
|
| 43 |
}
|
| 44 |
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
"do_lower_case": true,
|
| 49 |
+
"eos_token": "</s>",
|
| 50 |
+
"errors": "replace",
|
| 51 |
"extra_special_tokens": {},
|
| 52 |
+
"mask_token": "<mask>",
|
| 53 |
+
"max_len": 512,
|
| 54 |
"model_max_length": 512,
|
| 55 |
+
"pad_token": "<pad>",
|
| 56 |
+
"sep_token": "</s>",
|
| 57 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 58 |
+
"trim_offsets": true,
|
| 59 |
+
"unk_token": "<unk>"
|
|
|
|
| 60 |
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|