const output = await replicate.run(
  "nomagick/chatglm3-6b-32k:0b72c2a81326d09323a3a39689323b09ac9759609c0134ae59c9f2f683ff4cdb",
  {
    input: {
      top_p: 0.8,
      prompt: "<|system|>\nYou are a helpful assistant\n<|user|>\n请使用英文重复这段话：\"为了使模型生成最优输出，当使用 ChatGLM3-6B 时需要使用特定的输入格式，请按照示例格式组织输入。\"\n<|assistant|>\n",
      max_tokens: 2048,
      temperature: 0.75
    }
  }
);

console.log(output);

output = replicate.run(
    "nomagick/chatglm3-6b-32k:0b72c2a81326d09323a3a39689323b09ac9759609c0134ae59c9f2f683ff4cdb",
    input={
        "top_p": 0.8,
        "prompt": "<|system|>\nYou are a helpful assistant\n<|user|>\n请使用英文重复这段话：\"为了使模型生成最优输出，当使用 ChatGLM3-6B 时需要使用特定的输入格式，请按照示例格式组织输入。\"\n<|assistant|>\n",
        "max_tokens": 2048,
        "temperature": 0.75
    }
)

# The nomagick/chatglm3-6b-32k model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/nomagick/chatglm3-6b-32k/api#output-schema
    print(item, end="")

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "0b72c2a81326d09323a3a39689323b09ac9759609c0134ae59c9f2f683ff4cdb",
    "input": {
      "top_p": 0.8,
      "prompt": "<|system|>\\nYou are a helpful assistant\\n<|user|>\\n请使用英文重复这段话：\\"为了使模型生成最优输出，当使用 ChatGLM3-6B 时需要使用特定的输入格式，请按照示例格式组织输入。\\"\\n<|assistant|>\\n",
      "max_tokens": 2048,
      "temperature": 0.75
    }
  }' \
  https://api.replicate.com/v1/predictions