Update README.md

README.md

@@ -12,15 +12,17 @@ tags:
 ## Description:
 CodeLlama-7B-QML is a fine-tuned model for code completion tasks in Qt's Markup Language (QML). 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 79% on the QML100 Fill-In-the-Middle code completion benchmark for Qt 6-compliant code. In comparison, other models scored:
-- CodeLlama-13B-QML: 86%
+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%
-- Claude 3.5 Sonnet: 68%
+- Codestral: 69%
 - CodeLlama 13B: 66%
 - GPT-4o: 62%
 - CodeLlama 7B: 61%
 
-This model was fine-tuned based on raw data from over 5000 human-created QML code snippets using the LoRa fine-tuning method. CodeLlama-7B-QML is not optimized for the creation of Qt5-release compliant, C++, or Python code.
+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 Qt5-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](https://github.com/meta-llama/llama/blob/main/LICENSE), [acceptable use policy](https://github.com/meta-llama/llama/blob/main/USE_POLICY.md) and [Meta’s privacy policy](https://www.facebook.com/privacy/policy/). By using this model, you are furthermore agreeing to the [Qt AI Model terms & conditions](https://www.qt.io/terms-conditions/ai-services/model-use). 
@@ -51,8 +53,9 @@ 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": 0.2,
-  "top_p": 0.9,
+  "temperature": 0,
+  "top_p": 1,
+  "repettion_penalty": 1.05,
   "num_predict": 500,
   "stop": ["<SUF>", "<PRE>", "</PRE>", "</SUF>", "< EOT >", "\\end", "<MID>", "</MID>", "##"]
 }'
@@ -74,7 +77,7 @@ The HuggingFace repository contains all necessary components including the .safe
 
 
 ## Model Version:
-v1.0
+v2.0
 
 ## Attribution:
 CodeLlama-7B is a model of the Llama 2 family. Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.