Update README.md
Browse files
README.md
CHANGED
|
@@ -15,10 +15,15 @@ CodeLlama-13B-QML is a large language model customized by the Qt Company for Fil
|
|
| 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 |
|
| 17 |
CodeLlama-7B-QML: 79%
|
|
|
|
| 18 |
Claude 3.7 Sonnet: 76%
|
|
|
|
| 19 |
Claude 3.5 Sonnet: 68%
|
|
|
|
| 20 |
CodeLlama 13B: 66%
|
|
|
|
| 21 |
GPT-4o: 62%
|
|
|
|
| 22 |
CodeLlama 7B: 61%
|
| 23 |
|
| 24 |
This model was fine-tuned based on raw data from over 5000 human-created QML code snippets using the LoRa fine-tuning method. CodeLlama-13B-QML is not optimised for the creation of Qt5-release compliant, C++, or Python code.
|
|
|
|
| 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 |
|
| 17 |
CodeLlama-7B-QML: 79%
|
| 18 |
+
|
| 19 |
Claude 3.7 Sonnet: 76%
|
| 20 |
+
|
| 21 |
Claude 3.5 Sonnet: 68%
|
| 22 |
+
|
| 23 |
CodeLlama 13B: 66%
|
| 24 |
+
|
| 25 |
GPT-4o: 62%
|
| 26 |
+
|
| 27 |
CodeLlama 7B: 61%
|
| 28 |
|
| 29 |
This model was fine-tuned based on raw data from over 5000 human-created QML code snippets using the LoRa fine-tuning method. CodeLlama-13B-QML is not optimised for the creation of Qt5-release compliant, C++, or Python code.
|