Kimang18/gemma-3-1b-khmer-mlx-q4

This model Kimang18/gemma-3-1b-khmer-mlx-q4 was converted to MLX format from mlx-community/gemma-3-1b-it-bf16 after finetuning by Dr. Kimang KHUN on dataset rinabuoy/alpaca-khmer-cleaned using mlx-lm version 0.26.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("Kimang18/gemma-3-1b-khmer-mlx-q4")

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)