Hugging Face's logo

cisco-ai
/
SecureBERT2.0-biencoder

Sentence Similarity
sentence-transformers
Safetensors
English
modernbert
feature-extraction
dense
securebert
IR
docembedding
Generated from Trainer
dataset_size:35705
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Model card Files
xet
Community
cisco-ehsan commited on
Commit
8c9db25
·
verified ·
1 Parent(s): d6ef5b7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -4,7 +4,7 @@ license: apache-2.0
4
  language:
5
  - en
6
  base_model:
7
- - CiscoAITeam/SecureBERT2.0-base
8
  pipeline_tag: sentence-similarity
9
  library_name: sentence-transformers
10
  tags:
@@ -30,9 +30,9 @@ widget:
30
  programs
31
  ---
32
 
33
- # Model Card for CiscoAITeam/SecureBERT2.0-biencoder
34
 
35
- The **SecureBERT 2.0 Bi-Encoder** is a cybersecurity-domain sentence-similarity and document-embedding model fine-tuned from [SecureBERT 2.0](https://huggingface.co/CiscoAITeam/SecureBERT2.0-base).
36
  It independently encodes queries and documents into a shared vector space for **semantic search**, **information retrieval**, and **cybersecurity knowledge retrieval**.
37
 
38
  ---
@@ -41,14 +41,14 @@ It independently encodes queries and documents into a shared vector space for **
41
 
42
  ### Model Description
43
 
44
- - **Developed by:** Cisco AI Team
45
  - **Model type:** Bi-Encoder (Sentence Transformer)
46
  - **Architecture:** ModernBERT backbone with dual encoders
47
  - **Max sequence length:** 1024 tokens
48
  - **Output dimension:** 768
49
  - **Language:** English
50
  - **License:** Apache-2.0
51
- - **Finetuned from:** [CiscoAITeam/SecureBERT2.0-base](https://huggingface.co/CiscoAITeam/SecureBERT2.0-base)
52
 
53
  ---
54
 
@@ -111,7 +111,7 @@ pip install -U sentence-transformers
111
  ```python
112
  from sentence_transformers import SentenceTransformer
113
 
114
- model = SentenceTransformer("CiscoAITeam/SecureBERT2.0-biencoder")
115
 
116
  sentences = [
117
  "How would you use Amcache analysis to detect fileless malware?",
@@ -197,7 +197,7 @@ The model was optimized to maximize semantic similarity between relevant cyberse
197
 
198
  ## Model Card Authors
199
 
200
- Cisco AI Team
201
 
202
  ## Model Card Contact
203
- For inquiries, please contact [Cisco AI Team](eaghaei@cisco.com)
 
4
  language:
5
  - en
6
  base_model:
7
+ - CiscoAI/SecureBERT2.0-base
8
  pipeline_tag: sentence-similarity
9
  library_name: sentence-transformers
10
  tags:
 
30
  programs
31
  ---
32
 
33
+ # Model Card for CiscoAI/SecureBERT2.0-biencoder
34
 
35
+ The **SecureBERT 2.0 Bi-Encoder** is a cybersecurity-domain sentence-similarity and document-embedding model fine-tuned from [SecureBERT 2.0](https://huggingface.co/CiscoAI/SecureBERT2.0-base).
36
  It independently encodes queries and documents into a shared vector space for **semantic search**, **information retrieval**, and **cybersecurity knowledge retrieval**.
37
 
38
  ---
 
41
 
42
  ### Model Description
43
 
44
+ - **Developed by:** Cisco AI
45
  - **Model type:** Bi-Encoder (Sentence Transformer)
46
  - **Architecture:** ModernBERT backbone with dual encoders
47
  - **Max sequence length:** 1024 tokens
48
  - **Output dimension:** 768
49
  - **Language:** English
50
  - **License:** Apache-2.0
51
+ - **Finetuned from:** [CiscoAI/SecureBERT2.0-base](https://huggingface.co/CiscoAI/SecureBERT2.0-base)
52
 
53
  ---
54
 
 
111
  ```python
112
  from sentence_transformers import SentenceTransformer
113
 
114
+ model = SentenceTransformer("CiscoAI/SecureBERT2.0-biencoder")
115
 
116
  sentences = [
117
  "How would you use Amcache analysis to detect fileless malware?",
 
197
 
198
  ## Model Card Authors
199
 
200
+ Cisco AI
201
 
202
  ## Model Card Contact
203
+ For inquiries, please contact [Cisco AI](eaghaei@cisco.com)