Holodeck Phi-3.5 (LoRA Fine-Tuned)

Phi-3.5-mini-instruct fine-tuned on VMware Holodeck documentation using LoRA.

Quick Start with Ollama or Docker model

# Download and run directly from HF
ollama run hf.co/netwninja82/holodeck-phi35-gguf:Q4_K_M

OR

docker model run hf.co/netwninja82/holodeck-phi35-gguf:Q4_K_M

Model Details

  • Base model: microsoft/Phi-3.5-mini-instruct
  • Fine-tuning: LoRA (rank 64, alpha 128)
  • Quantization: Q4_K_M
  • Training data: VMware Holodeck documentation (RAG-style)

Key Facts

Best Usage

For best accuracy, use with RAG retrieval to provide context before answering.

Downloads last month
4
GGUF
Model size
4B params
Architecture
phi3
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for netwninja82/holodeck-phi35-gguf

Quantized
(170)
this model