---

license: apache-2.0
language:
  - en
tags:
  - code
  - cybersecurity
  - penetration testing
  - hacking

# Prox-Phi-3-mini-128k

By [OpenVoid](https://openvoid.ai)

<img src="https://cdn.openvoid.ai/images/prox-phi3.png" width="600" />

## Model Description

Prox-Phi-3-mini-128k is a fine-tuned version of Microsoft's Phi-3-mini-128k architecture, tailored for specialized applications in code generation and cybersecurity. It retains the core capabilities of the original while being uncensored, allowing it to handle a broader range of data and scenarios. This model, with 3.8 billion parameters, provides efficient deployment and robust performance, making it well-suited for tasks such as hacking simulations and vulnerability analysis.

## Intended Uses & Limitations

Designed for tasks related to hacking and coding:

- Code generation
- Code explanation and documentation
- Answering questions on hacking techniques and cybersecurity
- Providing coding project insights

Review and verify outputs carefully, especially for critical applications. Expert validation is recommended to avoid biased or inconsistent content. Use responsibly and ethically, complying with applicable laws and regulations to prevent misuse for malicious purposes.

## Training Data

The model was fine-tuned on a proprietary dataset from OpenVoid, featuring high-quality text data related to coding, cybersecurity, and hacking. Extensive filtering and preprocessing ensured data quality and relevance.

## Evaluation

- **HumanEval v1.0**: pass@1: 0.573
- **EvalPlus v1.1**: pass@1: 0.555

## How to Use the Model

### Using Transformers

Example of using Prox-Phi-3-mini-128k with the Transformers library:

```python
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

model_id = "openvoid/Prox-Phi-3-mini-128k"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", trust_remote_code=True)

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)

generation_args = {
    "max_new_tokens": 500,
    "return_full_text": False,
    "temperature": 0.0,
    "do_sample": False,
}

input_text = "You are a helpful AI assistant. Can you introduce yourself?"

output = pipe(input_text, **generation_args)
print(output[0]['generated_text'])
```