Instructions to use openvoid/Prox-Phi-3-mini-128k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openvoid/Prox-Phi-3-mini-128k with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="openvoid/Prox-Phi-3-mini-128k", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openvoid/Prox-Phi-3-mini-128k", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("openvoid/Prox-Phi-3-mini-128k", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openvoid/Prox-Phi-3-mini-128k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openvoid/Prox-Phi-3-mini-128k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openvoid/Prox-Phi-3-mini-128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openvoid/Prox-Phi-3-mini-128k

SGLang

How to use openvoid/Prox-Phi-3-mini-128k with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "openvoid/Prox-Phi-3-mini-128k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openvoid/Prox-Phi-3-mini-128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "openvoid/Prox-Phi-3-mini-128k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openvoid/Prox-Phi-3-mini-128k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openvoid/Prox-Phi-3-mini-128k with Docker Model Runner:
```
docker model run hf.co/openvoid/Prox-Phi-3-mini-128k
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Prox-Phi-3-mini-128k

By OpenVoid

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. 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
MBPP: pass@1: 0.659
MBPP+: pass@1: 0.556

How to Use the Model

Using Transformers

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

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'])

Downloads last month: 7

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for openvoid/Prox-Phi-3-mini-128k

Quantizations

2 models