linkedin-8bit-phi4 / README.md
SkyR's picture
Update README.md
8b6f0ac verified
metadata
language:
  - en
base_model:
  - microsoft/Phi-4-mini-instruct
pipeline_tag: text-generation
tags:
  - professional
  - linkedin
  • Parameter-efficient, instruction-fine-tuned phi-4-mini model.

  • Uses LoRA for fine-tuning.

  • Trained on LinkedIn posts from various themes.

  • Training details:

    • Training size: 2643
    • Quantization: 8-bit
    • Optimizer: AdamW
    • Learning Rate: 1e-4
    • Epochs: 1
    • Train Batch size: 1
    • Eval Batch size: 4
    • Gradient accumulation steps: 8
    • Sequence length: 412
  • LoRA configs:

    • Rank: 16
    • Alpha: 16
    • Dropout: 0.05