Decisions Lab HK Models
Collection
Fine-tuned for Hong Kong with a proprietary dataset, our models excel in cultural sensitivity and local contextual awareness.
•
5 items
•
Updated
The Model decisionslab/phi-4-4bit-HK was converted to MLX format from microsoft/phi-4 using mlx-lm version 0.21.1.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("decisionslab/phi-4-4bit-HK")
prompt = "hello"
if tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
Base model
microsoft/phi-4