legolasyiu
commited on
Commit
β’
1e971f5
1
Parent(s):
368c114
Update README.md
Browse files
README.md
CHANGED
@@ -15,6 +15,9 @@ pipeline_tag: text-generation
|
|
15 |
|
16 |
EpistemeAI/Iceball-Phi-3.5-mini-instruct-shareGPT-v1.0 is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.
|
17 |
|
|
|
|
|
|
|
18 |
π‘ [Phi-3 Portal](https://azure.microsoft.com/en-us/products/phi-3) <br>
|
19 |
π° [Phi-3 Microsoft Blog](https://aka.ms/phi3.5-techblog) <br>
|
20 |
π [Phi-3 Technical Report](https://arxiv.org/abs/2404.14219) <br>
|
|
|
15 |
|
16 |
EpistemeAI/Iceball-Phi-3.5-mini-instruct-shareGPT-v1.0 is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length. The model underwent a rigorous enhancement process, incorporating both supervised fine-tuning, proximal policy optimization, and direct preference optimization to ensure precise instruction adherence and robust safety measures.
|
17 |
|
18 |
+
<script type='text/javascript' src='https://storage.ko-fi.com/cdn/widget/Widget_2.js'></script><script type='text/javascript'>kofiwidget2.init('Support Me on Ko-fi', '#29abe0', 'C0C8127LWN');kofiwidget2.draw();</script>
|
19 |
+
|
20 |
+
|
21 |
π‘ [Phi-3 Portal](https://azure.microsoft.com/en-us/products/phi-3) <br>
|
22 |
π° [Phi-3 Microsoft Blog](https://aka.ms/phi3.5-techblog) <br>
|
23 |
π [Phi-3 Technical Report](https://arxiv.org/abs/2404.14219) <br>
|