File size: 863 Bytes
961db60 abb889e 961db60 |
1 2 3 4 5 6 7 8 9 10 |
<p>
This open-source model was created by <a target="_blank" href="https://www.microsoft.com/">Microsoft<a>.
You can find the release blog post <a target="_blank" href="https://azure.microsoft.com/en-us/blog/introducing-phi-3-redefining-whats-possible-with-slms/">here</a>.
The model is available on the huggingface hub: <a target="_blank" href="https://huggingface.co/microsoft/Phi-3-mini-128k-instruct">https://huggingface.co/microsoft/Phi-3-mini-128k-instruct</a>.
The model has 16x3.8B parameters with 6.6B active parameters, and supports up to 128K token contexts.
Even though this model supports system messages, we evaluate this model as user-message-only model
(the persona is induced by sending the user message "You are <persona>" followed by a manually set "OK" as the assistant's response)
as it worked better.
</p>
|