Instructions to use Threatthriver/phi4-finetuned-16bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Threatthriver/phi4-finetuned-16bit with Transformers:

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

pipe = pipeline("text-generation", model="Threatthriver/phi4-finetuned-16bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Threatthriver/phi4-finetuned-16bit", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Threatthriver/phi4-finetuned-16bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Threatthriver/phi4-finetuned-16bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Threatthriver/phi4-finetuned-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Threatthriver/phi4-finetuned-16bit

SGLang

How to use Threatthriver/phi4-finetuned-16bit 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 "Threatthriver/phi4-finetuned-16bit" \
    --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": "Threatthriver/phi4-finetuned-16bit",
		"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 "Threatthriver/phi4-finetuned-16bit" \
        --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": "Threatthriver/phi4-finetuned-16bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Threatthriver/phi4-finetuned-16bit with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Threatthriver/phi4-finetuned-16bit to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Threatthriver/phi4-finetuned-16bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Threatthriver/phi4-finetuned-16bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Threatthriver/phi4-finetuned-16bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use Threatthriver/phi4-finetuned-16bit with Docker Model Runner:
```
docker model run hf.co/Threatthriver/phi4-finetuned-16bit
```

Threatthriver/phi4-finetuned-16bit Model

Developed by: Threatthriver

License: Apache-2.0

Fine-tuned from model: unsloth/phi-4-unsloth-bnb-4bit (https://huggingface.co/unsloth/phi-4-unsloth-bnb-4bit)

Model Description:

This PHI-4 model, named Threatthriver/phi4-finetuned-16bit, was fine-tuned by Threatthriver, potentially for applications in cybersecurity, threat intelligence, or related domains. It was trained using Unsloth (https://github.com/unslothai/unsloth) and Hugging Face's TRL library, which allowed for a 2x faster training process. The model is based on the unsloth/phi-4-unsloth-bnb-4bit base model. It was fine-tuned and saved in 16-bit precision.

Intended Use:

This model is intended for research and development purposes. Specifically, it may be suitable for:

Text generation related to cybersecurity topics.
Experimentation with threat intelligence analysis.
Applications involving security automation.

Please adapt this section based on the actual intended use of your model.

Training Details:

The model was fine-tuned using the Unsloth library, known for its efficiency in training large language models. The base model unsloth/phi-4-unsloth-bnb-4bit was initially quantized to 4-bit using bitsandbytes (bnb) for reduced memory footprint and faster training. This fine-tuned version, Threatthriver/phi4-finetuned-16bit, was then saved in 16-bit precision.

How to Use:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Threatthriver/phi4-finetuned-16bit"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

input_text = "Example input text related to cybersecurity..."
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") # If using GPU

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))

Replace input_text with your specific use case.

Disclaimer:

This model is provided as-is, and no guarantees are made regarding its performance or suitability for any specific task. Use it at your own risk.

Acknowledgements:

Trained 2x faster with Unsloth (https://github.com/unslothai/unsloth) and Huggingface's TRL library.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for Threatthriver/phi4-finetuned-16bit

Base model

microsoft/phi-4

Quantized

unsloth/phi-4-unsloth-bnb-4bit

Finetuned

(354)

this model