Skip to main content

FIM Completion

In FIM (Fill In the Middle) completion, users can provide a prefix and an optional suffix, and the model fills in the content in between. FIM is commonly used for content continuation, code completion, and similar scenarios.

Notes​​

  1. The maximum completion length for the model is 4K.
  2. The currently available model is qwen2.5-coder-32b-instruct.

Sample Code​​

The following is a complete Python code example for FIM completion. In this example, we provide the beginning and end of a Fibonacci sequence function and let the model fill in the middle.

from openai import OpenAI

client = OpenAI(
    api_key="<your api key>",
    base_url="https://live-turing.cn.llm.tcljd.com/api/v1",
)

response = client.completions.create(
    model="qwen2.5-coder-32b-instruct",
    prompt="def fib(a):",
    suffix="    return fib(a-1) + fib(a-2)",
    max_tokens=128
)
print(response.choices[0].text)

Configure the Continue Code Completion Plugin​​

Continue is a VSCode plugin that supports code completion. You can refer to this document to configure Continue for code completion functionality.

Reference configuration example — note that provider should be set to openai:

models:
  - name: <your name>
    provider: openai
    model: qwen2.5-coder-32b-instruct
    apiKey: <your api key>
    apiBase: https://live-turing.cn.llm.tcljd.com/api/v1