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.