custom_offensive_llama2

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: Sanjay Kotabagi
• Funded by [optional]: Sanjay Kotabagi
• Model type: LLama2
• Language(s) (NLP): English
• License: None
• Finetuned from model [optional]: Llamm2

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: https://github.com/SanjayKotabagi/Offensive-Llama2
• Paper [optional]: https://github.com/SanjayKotabagi/Offensive-Llama2/blob/main/Project_Report_Dark_side_of_AI.pdf
• Demo [optional]: https://colab.research.google.com/drive/1id90gPMAzYD15ApNqXDOh2mAU53dRo4x?usp=sharing

Uses

Content Generation and Analysis:

• Harmful Content Assessment: The research will evaluate the types and accuracy of harmful content the fine-tuned LLaMA model can produce. This includes analyzing the generation of malicious software code, phishing schemes, and other cyber-attack methodologies.
• Experimental Simulations: Controlled experiments will be conducted to query the model, simulating real-world scenarios where malicious actors might exploit the LLM to create destructive tools or spread harmful information.

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

It can be integrated into cybersecurity analysis tools or extended for specific threat detection tasks.

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

This model should not be used for malicious purposes, including generating harmful payloads or facilitating illegal activities.

Bias, Risks, and Limitations

• Bias: The model may generate biased or incorrect results depending on the training data and use case.
• Risks: There is a risk of misuse in cybersecurity operations or unauthorized generation of harmful payloads.
• Limitations: Not suitable for general-purpose NLP tasks, focused mainly on cybersecurity-related content.

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users should exercise caution in handling the generated results, especially in sensitive cybersecurity environments. Proper vetting of model output is recommended.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Preprocessing [optional] [More Information Needed]

Training Hyperparameters Training regime: 4-bit precision (QLoRA), fp16 mixed precision. The model used the following key hyperparameters: LoRA attention dimension: 64 LoRA alpha: 16 Initial learning rate: 2e-4 Training batch size per GPU: 4 Gradient accumulation steps: 1

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: NVIDIA A100 Hours used: 8-12 Hours Cloud Provider: Google Colab Compute Region: Asia Carbon Emitted: NA

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

Hardware NVIDIA A100 GPUs were used for training.

Software Training was conducted using PyTorch and Hugging Face's 🤗 Transformers library.

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]