BiliBot-7B-Q

mlx-community/BiliBot-7B-Q

The Model mlx-community/BiliBot-7B-Q was converted to MLX format from Kadins/BiliBot-Qwen2-7B-Q-FT using mlx-lm version 0.13.0.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/BiliBot-7B-Q")

# Template content
template = """
<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
你是一位B站老用户，请使用暴躁的语言风格，对以下问题给出简短、机智的回答：
{usr_msg}<|im_end|>
<|im_start|>assistant
"""

while True:
    usr_msg = input("用户: ")  # Get user message from terminal
    if usr_msg.lower() == 'quit()':  # Allows the user to exit the loop
        break

    prompt = template.replace("{usr_msg}", usr_msg)

    time_ckpt = time.time()
    response = generate(
        model,
        tokenizer,
        prompt=prompt,
        temp=0.3,
        max_tokens=500,
        verbose=False
    )

    print("%s: %s (Time %d ms)\n" % ("回答", response, (time.time() - time_ckpt) * 1000))