Eduardo Alvarez comments

Results 5 comments of


                                            Eduardo Alvarez

AssertionError: Fail to convert pytorch model with 'Intel/neural-chat-7b-v3-3' WOQ

sure, I'll give this a try. Thank you!

SageMaker does not support Transformers 4.34.1 which is required by ITREX

Vincy, the problem is that if you try and install anything other than 4.34.1, you get an error that doesn't allow you to complete installation. ![image](https://github.com/intel/intel-extension-for-transformers/assets/57263404/a9e59e17-d2d7-4f2a-8403-4b3770768b78)

Lab 6 not working as "Falcon has now been fully ported into the Hugging Face transformers library"

Hello @paleze the warning should not prevent the lab from running. Can you please try again?

[Performance]: When deployed DeepSeek-V3 on 8*H20(96GB), maximum model length only reaches 6500 using vllm, but with sglang can achieve 163840.

anyone know why the 163840 isn't reported by DeepSeek in their model card? Is it in the paper? I might have missed it.

Typos in Documentation (github io)

Awesome, feel free to close.