def main()

in fastchat/serve/huggingface_api.py [0:0]

• 33 lines of code
• 3 McCabe index (conditional complexity)

def main(args):
    # Load model
    model, tokenizer = load_model(
        args.model_path,
        device=args.device,
        num_gpus=args.num_gpus,
        max_gpu_memory=args.max_gpu_memory,
        load_8bit=args.load_8bit,
        cpu_offloading=args.cpu_offloading,
        revision=args.revision,
        debug=args.debug,
    )

    # Build the prompt with a conversation template
    msg = args.message
    conv = get_conversation_template(args.model_path)
    conv.append_message(conv.roles[0], msg)
    conv.append_message(conv.roles[1], None)
    prompt = conv.get_prompt()

    # Run inference
    inputs = tokenizer([prompt], return_tensors="pt").to(args.device)
    output_ids = model.generate(
        **inputs,
        do_sample=True if args.temperature > 1e-5 else False,
        temperature=args.temperature,
        repetition_penalty=args.repetition_penalty,
        max_new_tokens=args.max_new_tokens,
    )

    if model.config.is_encoder_decoder:
        output_ids = output_ids[0]
    else:
        output_ids = output_ids[0][len(inputs["input_ids"][0]) :]
    outputs = tokenizer.decode(
        output_ids, skip_special_tokens=True, spaces_between_special_tokens=False
    )

    # Print results
    print(f"{conv.roles[0]}: {msg}")
    print(f"{conv.roles[1]}: {outputs}")