ghosthets commited on
Commit
734e2af
ยท
verified ยท
1 Parent(s): 066c18d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -1
README.md CHANGED
@@ -6,5 +6,90 @@ colorTo: yellow
6
  sdk: gradio
7
  pinned: false
8
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
 
10
- Edit this `README.md` markdown file to author your organization card.
 
6
  sdk: gradio
7
  pinned: false
8
  ---
9
+ ![Dex Banner](https://cdn-avatars.huggingface.co/v1/production/uploads/678a345729f4e4a1d9941a70/vUjbA1a9NqShIYEfBEmQd.jpeg)
10
+
11
+ ---
12
+ license: apache-2.0
13
+ tags:
14
+ - text-generation
15
+ - cybersecurity
16
+ - chatbot
17
+ - transformers
18
+ - edge-device-friendly
19
+ - dex-ai
20
+ datasets:
21
+ - suryanshp1/kali-linux-pentesting-data
22
+ - AlicanKiraz0/All-CVE-Records-Training-Dataset
23
+ language:
24
+ - en
25
+ library_name: transformers
26
+ pipeline_tag: text-generation
27
+ ---
28
+
29
+ # ๐Ÿ›ก๏ธ Dex โ€” Cybersecurity Chatbot AI (Made by `ghosthets`)
30
+
31
+ **Dex** (Digital Exploit eXpert) is an AI model tailored for the cybersecurity and hacking community. It acts as a friendly chatbot that helps with:
32
+ - Cybersecurity topics
33
+ - Capture The Flag (CTF) guidance
34
+ - Basic exploit reasoning
35
+ - Code & payload understanding
36
+ - Custom AI assistant logic
37
+
38
+ ---
39
+
40
+ ## ๐Ÿ“Š Model Information
41
+
42
+ | Key Details | Value |
43
+ |-------------------|-------------------------------------|
44
+ | Model Name | `dexcommunity/dex` |
45
+ | Base Architecture | Causal Language Model |
46
+ | Framework | ๐Ÿค— Transformers |
47
+ | Optimized For | Edge devices (Raspberry Pi Zero etc)|
48
+ | Author | Gaurav Chouhan aka `ghosthets` |
49
+ | License | Apache-2.0 |
50
+
51
+ ---
52
+
53
+ ## โš™๏ธ Usage (Python Example)
54
+
55
+ ```python
56
+ from transformers import AutoTokenizer, AutoModelForCausalLM
57
+ import torch
58
+
59
+ tokenizer = AutoTokenizer.from_pretrained("dexcommunity/dex")
60
+ model = AutoModelForCausalLM.from_pretrained("dexcommunity/dex")
61
+
62
+ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
63
+ model.to(device)
64
+
65
+ def ask_dex(prompt):
66
+ inputs = tokenizer(f"User: {prompt}\nDex:", return_tensors="pt").to(device)
67
+ output = model.generate(inputs.input_ids, max_length=256, pad_token_id=tokenizer.eos_token_id)
68
+ return tokenizer.decode(output[0], skip_special_tokens=True).split("Dex:")[-1].strip()
69
+
70
+ print(ask_dex("Explain SQL Injection in simple words"))
71
+
72
+ โœ… Features
73
+
74
+ โœ… Lightweight & optimized for edge devices (e.g. Raspberry Pi Zero W/2W)
75
+ โœ… Helpful in CTF, Bug Bounty, and Penetration Testing topics
76
+ โœ… Trainable on your own dataset via LoRA or PEFT methods
77
+ โœ… Fine-tuned on initial cyber security corpora
78
+
79
+ ๐Ÿ”ฎ Future Plans
80
+
81
+ ๐Ÿง  Add OWASP Top 10 understanding
82
+ ๐Ÿ’ก Enhance with Exploit DB & CVE logic
83
+ ๐Ÿค– Hugging Face Space + GUI Gradio interface
84
+
85
+ ๐Ÿง  Made With ๐Ÿ’™ by
86
+ ๐Ÿ‘จโ€๐Ÿ’ป Gaurav Chouhan
87
+
88
+ Aka ghosthets ๐Ÿ‡ฎ๐Ÿ‡ณ
89
+ GitHub: ghosthets
90
+ LinkedIn: linkedin.com/in/ghosthets
91
+
92
+ ๐Ÿ“Ž License
93
+ Licensed under Apache-2.0. Use freely with attribution.
94
+
95