Lee Stott comments

Results 176 comments of


                                            Lee Stott

Example to use Phi 3.5 Vision to compare two images and/or multiple frames using ONNX/C#

Yes, you're correct. Each image is processed individually in the loop, and the results are handled separately for each image. To combine text and image tensors, you can create a...

[TRANSLATIONS] Call for Reviewers for our new translations.

translation is now automatic

conda env update breaks container building in WSL

@hinogi please retry requirements have been updated.

Issue with using Azure Open AI with courses

please use a gpt4o

Pip dependencys failing out but

This is being looked into

Azure OpenAI Phi-4-multimodel-instruct: 'auto' tool choice error when using runTools()

Hi @Junaid-Nazir-828 so you need to set a system prompt for Phi-4-mm-instruct see https://github.com/microsoft/PhiCookBook/issues/277 TypeScript Example: Using Tools with Phi-4-MM-Instruct Here's a TypeScript example showing how to use function calling...

Unable to Run Phi 3 and 3.5 vision on Mac [Chips M1 & M3] ~"Placeholder storage has not been allocated on MPS device!"

Here are a few suggestions to help you troubleshoot and potentially resolve this issue: Check PyTorch and Transformers Versions: Ensure that you're using compatible versions of PyTorch and the Hugging...

Microsoft Agent .NET samples not consistent

@koreyspace

Translated for-teachers in italian.md

Content is now auto translated

Phi-MM Generate Speed

Here are a few suggestions to potentially improve the inference speed. Batch Size: Ensure that you process a batch of inputs. Single input processing might be slower. Mixed Precision: Using...