Shital Shah
@sytelus.bsky.social
AI at Microsoft Research.
If universe is an optimizer, what is its loss function?
Code infra lead for Phi series of models.
Some Open Source Projects: Airsim, TensorWatch, Archai, NanuGPT
All opinions are my own.
If universe is an optimizer, what is its loss function?
Code infra lead for Phi series of models.
Some Open Source Projects: Airsim, TensorWatch, Archai, NanuGPT
All opinions are my own.
More about phi-4:
bsky.app/profile/syte...
bsky.app/profile/syte...
Are you ready for an early Christmas present from our team at Microsoft Research?
Introducing the most powerful smol model ever built in the world!
Welcome to Phi-4! 👇
Introducing the most powerful smol model ever built in the world!
Welcome to Phi-4! 👇
January 8, 2025 at 3:50 PM
More about phi-4:
bsky.app/profile/syte...
bsky.app/profile/syte...
HuggingFace Link:
huggingface.co/microsoft/ph...
huggingface.co/microsoft/ph...
microsoft/phi-4 · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 8, 2025 at 3:50 PM
HuggingFace Link:
huggingface.co/microsoft/ph...
huggingface.co/microsoft/ph...
We hope you will have as much fun playing and creating with this tiny beast of a model as we had building it.
Happy holiday chilln' for ya all🎄🎁.
Happy holiday chilln' for ya all🎄🎁.
December 13, 2024 at 3:37 AM
We hope you will have as much fun playing and creating with this tiny beast of a model as we had building it.
Happy holiday chilln' for ya all🎄🎁.
Happy holiday chilln' for ya all🎄🎁.
Paper: arxiv.org/abs/2412.08905
Model is available now to try in Azure: ai.azure.com/explore/mode...
What's better than tokens? Tokens with logits!!
Model is available now to try in Azure: ai.azure.com/explore/mode...
What's better than tokens? Tokens with logits!!
Phi-4 Technical Report
We present phi-4, a 14-billion parameter language model developed with a training recipe that is centrally focused on data quality. Unlike most language models, where pre-training is based primarily o...
arxiv.org
December 13, 2024 at 3:37 AM
Paper: arxiv.org/abs/2412.08905
Model is available now to try in Azure: ai.azure.com/explore/mode...
What's better than tokens? Tokens with logits!!
Model is available now to try in Azure: ai.azure.com/explore/mode...
What's better than tokens? Tokens with logits!!
This is the work of super hard working team.
Of course, none of this would have been possible without support from our amazing leadership team
Ece Kamar, Peter Lee.
Of course, none of this would have been possible without support from our amazing leadership team
Ece Kamar, Peter Lee.
December 13, 2024 at 3:37 AM
This is the work of super hard working team.
Of course, none of this would have been possible without support from our amazing leadership team
Ece Kamar, Peter Lee.
Of course, none of this would have been possible without support from our amazing leadership team
Ece Kamar, Peter Lee.
Phi-4 achieves this by pushing the art of synthetic data even further to induce reasoning abilities along with new advancements in post-training.
If you have been using Llama 3.x etc for reasoning tasks, you owe it to yourself to try out Phi-4!
If you have been using Llama 3.x etc for reasoning tasks, you owe it to yourself to try out Phi-4!
December 13, 2024 at 3:37 AM
Phi-4 achieves this by pushing the art of synthetic data even further to induce reasoning abilities along with new advancements in post-training.
If you have been using Llama 3.x etc for reasoning tasks, you owe it to yourself to try out Phi-4!
If you have been using Llama 3.x etc for reasoning tasks, you owe it to yourself to try out Phi-4!
Personally, since I started working on Phi project at its inception, this is my most favorite model that we have ever shipped.
Remember prompts that many frontier models including o1-preview struggled with? Phi-4 gave correct answer super fast!
Remember prompts that many frontier models including o1-preview struggled with? Phi-4 gave correct answer super fast!
December 13, 2024 at 3:37 AM
Personally, since I started working on Phi project at its inception, this is my most favorite model that we have ever shipped.
Remember prompts that many frontier models including o1-preview struggled with? Phi-4 gave correct answer super fast!
Remember prompts that many frontier models including o1-preview struggled with? Phi-4 gave correct answer super fast!
Apply here today:
jobs.careers.microsoft.com/global/en/jo...
This is a rare and unique opportunity to work on some very rewarding reasoning problems along side the members of Phi team and our product group partners.
Excited? Apply TODAY!!
We look forward to talk with you soon!
jobs.careers.microsoft.com/global/en/jo...
This is a rare and unique opportunity to work on some very rewarding reasoning problems along side the members of Phi team and our product group partners.
Excited? Apply TODAY!!
We look forward to talk with you soon!
Search Jobs | Microsoft Careers
https://jobs.careers.microsoft.com/global/en/job/…
December 11, 2024 at 12:26 AM
Apply here today:
jobs.careers.microsoft.com/global/en/jo...
This is a rare and unique opportunity to work on some very rewarding reasoning problems along side the members of Phi team and our product group partners.
Excited? Apply TODAY!!
We look forward to talk with you soon!
jobs.careers.microsoft.com/global/en/jo...
This is a rare and unique opportunity to work on some very rewarding reasoning problems along side the members of Phi team and our product group partners.
Excited? Apply TODAY!!
We look forward to talk with you soon!