PeterSchneider commited on
Commit
2e738cf
·
verified ·
1 Parent(s): f810886

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -10,7 +10,7 @@ tags:
10
  # Model Overview
11
 
12
  ## Description:
13
- CodeLlama-7B-QML is a large language model for code completion tasks in the 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.
14
 
15
  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:
16
  - CodeLlama-13B-QML: 79%
@@ -20,7 +20,7 @@ This model reaches a score of 79% on the QML100 Fill-In-the-Middle code completi
20
  - GPT-4o: 62%
21
  - CodeLlama 7B: 61%
22
 
23
- 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 optimised for the creation of Qt5-release compliant, C++, or Python code.
24
 
25
  ## Terms of use:
26
  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).
 
10
  # Model Overview
11
 
12
  ## Description:
13
+ 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.
14
 
15
  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:
16
  - CodeLlama-13B-QML: 79%
 
20
  - GPT-4o: 62%
21
  - CodeLlama 7B: 61%
22
 
23
+ 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.
24
 
25
  ## Terms of use:
26
  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).