continue调用1.5B小模型实现代码fast-apply

100tok/s生成速度，就问够不够fast？用过cursor的小伙伴一定对有个功能印象深刻，那就是fast apply功能。只要点一下，就可以把对话框中AI生成的代码快速地应用到编辑器的当前代码文件里， 然后下一步就是对比变更，accept或者reject代码块,相比于要手动从对话框复制代码到编辑器里粘贴修改，这个方式非常高效方便，是cursor的杀手锏功能.

现在可以通过vscode插件continue使用本地的小模型来实现这个功能，这个模型就是Qwen2.5-Coder-1.5b。1.5B的GGUF量化模型在我本地电脑M2 Max上通过LMStudio来跑，测试速度大约是q8_0 100 tok/s，q4_0 140 tok/s，fp16 70 tok/s，7B版本的q4_0 40 tok/s。兼顾性能和速度的话，我还是选择了1.5B的q8_0版本。

这件事起因是我看到一个专门用于fast apply的微调模型FastApply-1.5B-v1.0，是通过微调qwen2.5-coder-1.5B和7B模型实现的，专门用于代码合并fast apply功能的模型，准确率比原版有提升。

我试图把它接入到continue里，不知道continue的小伙伴可以看这个视频入门（continue开源AI代码编程助手-自定义api-SiliconFlow硅基流动与deepseek配置教程-哔哩哔哩）。可惜它的输出格式是<updated-code>[Full-complete updated file]</updated-code>，要通过修改continue源码来解析模型生成的代码，这太复杂了，我就放弃折腾，直接用原版qwen2.5-coder-1.5B好了。

经过我粗略对比，原版容易删除注释和换行空格，没有那么守规矩。微调版输出更准确，但是原版能力也不差，可以使用，200行内的简单代码合并轻轻松松，并且1.5B既能支持fast apply，也可以支持代码补全fim，一个模型两个用途，本地运行非常划算。

下面是如何配置continue：

// ~/.continue/config.json
{
    "models": [
        {
            "title": "fastapply-1.5b-v1.0@f16",
            "model": "qwen2.5-coder-1.5b-instruct@q8_0",
            "apiBase": "http://192.168.8.110:5000/v1",
            "provider": "lmstudio",
            "contextLength": 16000,
            "completionOptions": {
                "maxTokens": 4000,
                "stop": [
                    "<|endoftext|>"
                ],
                "temperature": 0.01
            }
        }
    ],
    "tabAutocompleteModel": {
        "title": "ollama_model",
        "provider": "lmstudio",
        "model": "qwen2.5-coder-1.5b-instruct@q8_0",
        "template": "qwen",
        "apiBase": "http://192.168.8.110:5000/v1"
    },
    "modelRoles": {
        "applyCodeBlock": "fastapply-1.5b-v1.0@f16",
        "inlineEdit": "fastapply-1.5b-v1.0@f16"
    },
    "promptTemplates": {
        "edit": "<|im_start|>system\nYou are a codingassistant that helps merge code updates, ensuring everymodification is fully integrated.\n im_end |>\n< im_start>user\nMerge all changes from the <update> snippet into the<code> below.\n- Preserve the code's structure, order,comments, and indentation exactly.\n- Output only theupdated code, enclosed within markdown 、{{{language}}}tags.\n- Do not include any additionalyour update codetext,explanations, placeholders,ellipses, or code fencesIn<code>{{{codeToEdit}}}</code>\n<update>{{{userInput}}}</update>\nProvide the complete updated code.<|im_end |>\n<im_ start|>assistant\n"
    }
}

下面是js修改promptTemplate的方法，上面有字符模板就不需要了，已废弃

// ~/.continue/config.ts
export function modifyConfig(config: Config): Config {
    const gptEditPrompt: PromptTemplate = (_, otherData) => {
        // 原版enclosed within <updated-code> and </updated-code> tags
        // system You are a coding assistant that helps merge code updates
        // Do not include any additional text, explanations, placeholders, ellipses, or code fences.
        // 为了方便兼容改成markdown格式的
        // enclosed within markdown \`\`\`your update code\`\`\`
        const systemMessage =
            `<|im_start|>system You are a coding assistant that helps fix code and merge code updates, ensuring every modification is fully integrated.<|im_end|>`;
        const userMessage =
            `<|im_start|>user Merge all changes from the <update> snippet into the <code> below. - Preserve the code's structure, order, comments, and indentation exactly. - Output only the updated code, enclosed within markdown \`\`\`your update code\`\`\`. - Do not include any additional text, explanations, placeholders, ellipses.`;

        if (otherData ? .codeToEdit ? .trim().length === 0) {
            return `${systemMessage}
${userMessage}
<code>${otherData.prefix}[BLANK]${otherData.suffix}</code>
<update>${otherData.userInput}</update>
Provide the complete updated code.<|im_end|>
<|im_start|>assistant `;
        }

        // const codeBlock = `${otherData.prefix}<code>${otherData.codeToEdit}$</code>{otherData.suffix}`;  // 使用prefix, suffix
        const codeBlock = `<code>${otherData.codeToEdit}</code>`;
        const updateBlock = `<update>${otherData.userInput}</update>`;

        return `${systemMessage}
${userMessage}
${codeBlock}
${updateBlock}
Provide the complete updated code.<|im_end|>
<|im_start|>assistant `;
    };

    let modelName = "fastapply-1.5b-v1.0@f16"
    // Fix the model finding logic
    let applyModel = config.models.find(model => model.title === modelName);
    if (applyModel) {
        applyModel.promptTemplates = {
            edit: gptEditPrompt,
        };
        // console.log('done')
    } else {
        // console.warn('Model "fastapply-1.5b-v1.0@f16" not found in config.models');
    }
    return config;
}

我还向continue仓库提了一个issue，希望能兼容fastApply微调模型，欢迎跟踪进度。