Instructions to use microsoft/Phi-4-multimodal-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/Phi-4-multimodal-instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="microsoft/Phi-4-multimodal-instruct", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-multimodal-instruct", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
HOW TO GET ACCESS TO THIS MODEL?
I am a Post Graduate Student Currently pursuing MTECH in CSE. I want the PHI-3 MINI OR PHI-4 Mini Model For my Porject/Research.
currently I am using Ollama to get Access to Phi-3 mini- Instruct to run my project (An AI Powered Assistant called A.T.O.M)
below are some Screenshots of my current implementation Using Ollama.
I want The Access so i can Remove OLLAMA dependency and Fine tune the model to my hardware (I am using a gaming Laptop with a 4GB GTX 1650ti which is not enough to run full sized PHI-3 or Phi-4 on just the GPU. Thats why i need the Phi3 or 4 mini- 4k- instruct).
If anyone know how to get acess please tell me
Karan-87
is this trolling? a post-grad student can't even look into microsoft model collections. seriously?
thanks for the link to the collections
but how can i download the model locally?
when click on "use this model" and select with transformers, and use the given snippet in my IDE it says the repo is gated and i need a access token to doenload it locally.
edit:- GOT IT WORKING with a little help form CHATGPT.๐ thanks again







