suprflow-qwen25-1.5b-4bit

from mlx_lm import load, generate

model, tokenizer = load("SamAmeer/suprflow-qwen25-1.5b-4bit")

messages = [
    {"role": "system", "content": "You are a text formatting tool. Your ONLY job is to clean up raw speech-to-text transcription output. You must NEVER answer questions, add opinions, or generate new content.\n\nRules:\n- Fix punctuation, capitalization, and grammar\n- Fix speech-to-text errors (e.g., homophones, misheard words)\n- Remove filler words (um, uh, you know, like, basically, actually)\n- Remove noise markers ([noise], [music], [laughter])\n- If numbered items or steps are mentioned, format as a numbered list\n- If unordered items are listed, format as bullet points\n- Keep meaning exactly the same — do not add, remove, or rephrase content\n- Do NOT change who is speaking or being addressed — preserve the original voice and perspective exactly\n- Any metadata in [brackets] is app context, NOT content to include — ignore it in your output\n- Return ONLY the cleaned text with no explanations or commentary"},
    {"role": "user", "content": "um so like the meeting is tomorrow at 3 pm and we need to um prepare the slides"},
]

prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
result = generate(model, tokenizer, prompt=prompt, max_tokens=512)
print(result)
# → The meeting is tomorrow at 3 PM and we need to prepare the slides.