bha6kar's picture
Upload README.md with huggingface_hub
02bf6c6 verified
|
Raw
History Blame Contribute Delete
744 Bytes
metadata
base_model: mlx-community/Phi-4-mini-instruct-4bit
library_name: mlx
tags:
  - lora
  - mlx
  - finance

bha6kar/finance-lora-phi-4-mini

LoRA adapter fine-tuning mlx-community/Phi-4-mini-instruct-4bit on the gbharti/finance-alpaca financial instruction dataset with MLX.

  • Test perplexity: 33.933 (base) to 7.184 (tuned), across 3 seed(s).

Use

from mlx_lm import load, generate
model, tok = load("mlx-community/Phi-4-mini-instruct-4bit", adapter_path="<downloaded-adapter-dir>")

Produced by slm-training.