Model Overview

Description:

CodeLlama-7B-QML is a large language model customized by the Qt Company for Fill-In-The-Middle code completion tasks in the QML programming language, especially for Qt Quick Controls compliant with Qt 6 releases. The CodeLlama-7B-QML model is designed for software developers who want to run their code completion LLM locally on their computer.

This model reaches a score of 80% on the QML100 Fill-In-the-Middle code completion benchmark for Qt 6-compliant code. In comparison, other models scored:

• CodeLlama-13B-QML: 89%

• DeepSeek V3: 87%

• Claude 4 Sonnet: 81%

• Claude 3.7 Sonnet: 76%

• Codestral: 69%

• CodeLlama 13B: 66%

• GPT-4o: 62%

• CodeLlama 7B: 61%

This model was fine-tuned based on raw data from over 5500 human-created QML code snippets using the LoRa fine-tuning method. CodeLlama-7B-QML is not optimized for the creation of Qt 5-release compliant, C++, or Python code.

Terms of use:

By accessing this model, you are agreeing to the Llama 2 terms and conditions of the license, acceptable use policy and Meta’s privacy policy. By using this model, you are furthermore agreeing to the Qt AI Model terms & conditions.

How to run CodeLlama-7B-QML

Run the model with the following command in Ollama’s CLI: ollama run theqtcompany/codellama-7b-qml

Now, you can set and use CodeLlama-7B-QML as an LLM for code completions in the Qt AI Assistant or other coding assistants. If you want to test the model, you can write curl requests in Ollama’s CLI, as shown below.

curl -X POST http://localhost:11434/api/generate -d '{ "model": "theqtcompany/codellama-7b-qml", "Prompt": "<SUF>\n title: qsTr(\"Hello World\")\n}<PRE>import QtQuick\n\nWindow {\n width: 640\n height: 480\n visible: true\n<MID>", "stream": false, "temperature": 0, "top_p": 1, "repeat_penalty": 1.05, "num_predict": 500, "stop": ["<SUF>", "<PRE>", "</PRE>", "</SUF>", "< EOT >", "\\end", "<MID>", "</MID>", "##"] }'

In general, the prompt format for CodeLlama-7B-QML is:

"<SUF>{suffix}<PRE>{prefix}<MID>"

If there is no suffix, please use:

"<PRE>{prefix}<MID>"

Model Version: v3.0

Attribution: CodeLlama-7B is a model of the Llama 2 family. Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.