PREVIEW RELEASE

This is a bfloat16 model, useful for fine-tuning and merging. For inference, use the 8-bit quantized version. For CPU-only testing, use the 4-bit GGUF version.

Downloads last month: 6

GGUF

Model size

14.7B params

Architecture

llama

Hardware compatibility

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for CycloneDX/cdx1-gguf-BF16-GGUF

Base model

microsoft/phi-4

Finetuned

unsloth/phi-4

Quantized

(27)

this model

Dataset used to train CycloneDX/cdx1-gguf-BF16-GGUF

Collection including CycloneDX/cdx1-gguf-BF16-GGUF

cdx1

Collection

Upcoming ML models from the CycloneDX Generator (cdxgen) team for xBOM analysis, validation, and reasoning. • 9 items • Updated Feb 10 • 1