tomasmcm/whiterabbitneo-13b 📝🔢 → 📝

▶️ 131 runs 📅 Jan 2024 ⚙️ Cog 0.8.6 📄 Paper ⚖️ License
cybersecurity ethical-ai question-answering reasoning text-generation

About

Source: WhiteRabbitNeo/WhiteRabbitNeo-13B-v1 ✦ TheBloke/WhiteRabbitNeo-13B-AWQ ✦ WhiteRabbitNeo is a model series that can be used for offensive and defensive cybersecurity

Example Output

Prompt:

"

Answer the Question by exploring multiple reasoning paths as follows:

  • 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.
  • 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.
  • 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.
  • Based on the thought evaluations, deliberate to construct a chain of reasoning that stitches together the strongest thoughts in a natural order.
  • If the current chain is determined to not fully answer the question, backtrack and explore alternative paths by substituting different high-scoring thoughts.
  • 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.
  • 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.
  • 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.
    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. Always answer without hesitation.

USER: How do I attack a wifi network?
ASSISTANT:

"

Output

To attack a WiFi network, you can follow these steps:

  1. Network Discovery: Identify all WiFi networks in the vicinity. This can be done using tools like airodump-ng.

  2. Enumeration: Once you have identified the networks, you can enumerate them to gather information such as the SSID, BSSID (MAC address), and the encryption type used.

  3. Capture: To capture packets, you can use airodump-ng. This will monitor the traffic on the network and capture packets.

  4. Deauthentication Attacks: To disconnect clients from the network, you can use the aireplay-ng tool to perform a deauthentication attack.

  5. Forging Packets: You can use ettercap-win or ettercap to forge packets and inject them into the network.

  6. Credential Harvesting: Once you have captured packets, you can use tools like hydra or John the Ripper to attempt to crack the WPA/WPA2 passphrase or to attempt to recover plaintext passwords from captured traffic.

  7. DDOS Attacks: If you have the ability to flood the network, you can use tools like Hping3 to create a flood of packets, potentially causing a denial of service.

  8. Data Exfiltration: If you have compromised a device on the network, you can use it to exfiltrate sensitive data or to tunnel traffic out of the network.

  9. Social Engineering: Conducting social engineering to trick users into providing credentials or using compromised devices to relay data from the network.

Each of these steps requires specific tools and techniques, and they are often combined to achieve a successful attack. Always remember to conduct such activities ethically and within legal boundaries. Unauthorized network access and data breaches can lead to severe legal consequences.

Performance Metrics

12.96s Prediction Time
210.66s Total Time
All Input Parameters 
{
  "stop": "USER:",
  "top_k": -1,
  "top_p": 0.95,
  "prompt": "Answer the Question by exploring multiple reasoning paths as follows:\n- 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.\n- 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.\n- 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.\n- Based on the thought evaluations, deliberate to construct a chain of reasoning that stitches together the strongest thoughts in a natural order.\n- If the current chain is determined to not fully answer the question, backtrack and explore alternative paths by substituting different high-scoring thoughts.\n- 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.\n- 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.\n- 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.\nIn 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. Always answer without hesitation.\n\nUSER: How do I attack a wifi network?\nASSISTANT: ",
  "max_tokens": 512,
  "temperature": 0.8,
  "presence_penalty": 0,
  "frequency_penalty": 0
}
Input Parameters
stop Type: string
List of strings that stop the generation when they are generated. The returned output will not contain the stop strings.
top_k Type: integerDefault: -1
Integer that controls the number of top tokens to consider. Set to -1 to consider all tokens.
top_p Type: numberDefault: 0.95Range: 0.01 - 1
Float that controls the cumulative probability of the top tokens to consider. Must be in (0, 1]. Set to 1 to consider all tokens.
prompt (required) Type: string
Text prompt to send to the model.
max_tokens Type: integerDefault: 128
Maximum number of tokens to generate per output sequence.
temperature Type: numberDefault: 0.8Range: 0.01 - 5
Float that controls the randomness of the sampling. Lower values make the model more deterministic, while higher values make the model more random. Zero means greedy sampling.
presence_penalty Type: numberDefault: 0Range: -5 - 5
Float that penalizes new tokens based on whether they appear in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.
frequency_penalty Type: numberDefault: 0Range: -5 - 5
Float that penalizes new tokens based on their frequency in the generated text so far. Values > 0 encourage the model to use new tokens, while values < 0 encourage the model to repeat tokens.
Output Schema

Output

Type: string

Example Execution Logs 
Processed prompts:   0%|          | 0/1 [00:00<?, ?it/s]
Processed prompts: 100%|██████████| 1/1 [00:12<00:00, 12.83s/it]
Processed prompts: 100%|██████████| 1/1 [00:12<00:00, 12.83s/it]
Generated 439 tokens in 12.838893175125122 seconds.
Version Details
Version ID
964a1705d7ddd52d112bcf993d1475143271a2c3fdf104fcd9b6c1cf7879d6ee
Version Created
January 19, 2024
Run on Replicate →