Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,11 @@ tags:
|
|
| 11 |
<h2 style="text-align: center">Training Time: 1.85h</h2>
|
| 12 |
<hr>
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
Koss-7B is the smallest variant in the Koss series of neural network models developed by Kaleido AI for natural language processing. With 7 billion parameters, it retains much of the architecture and capabilities of the larger Koss models but requires less computation to run.
|
| 15 |
|
| 16 |
Koss-7B is intended for general NLP applications including text classification, language generation, question answering, translation, and dialogue. Its small size makes it suitable for applications with constraints on memory, compute, latency, or carbon emissions.
|
|
|
|
| 11 |
<h2 style="text-align: center">Training Time: 1.85h</h2>
|
| 12 |
<hr>
|
| 13 |
|
| 14 |
+
| Model | Average ⬆️ | ARC | HellaSwag | MMLU | TruthfulQA |
|
| 15 |
+
|:-------------------:|:------------:|:-------:|:---------:|:-------:|:----------:|
|
| 16 |
+
| NewstaR/Koss-7B-chat 📑 | 55.79 | 53.67 | 78.79 | 46.72 | 43.97 |
|
| 17 |
+
|
| 18 |
+
|
| 19 |
Koss-7B is the smallest variant in the Koss series of neural network models developed by Kaleido AI for natural language processing. With 7 billion parameters, it retains much of the architecture and capabilities of the larger Koss models but requires less computation to run.
|
| 20 |
|
| 21 |
Koss-7B is intended for general NLP applications including text classification, language generation, question answering, translation, and dialogue. Its small size makes it suitable for applications with constraints on memory, compute, latency, or carbon emissions.
|