Ekaterina Aidova
Ekaterina Aidova
> I'm seeing an error in the CI. It looks like the previous usage of the validator class needs updating. The error is on the Segment notebook but it's likely...
@echarlaix could you please take a look?
@dnoliver is it really necessary to use such old pytorch? As I can see in issue, downgrade on 2.2.2 should be enough
@dnoliver great, I also tested your notebook, it is also working for me. Should we put some message about proper driver version requirements to install (e.g. refer on this page...
@wgzintel @peterchen-intel maybe it is also will be good to introduce versioning into llm_bench? I think it may be more robust way for checking code version instead of commit id...
@peterchen-intel , yes, I think something similar will be fine, we have no setup, so I think we can combine them in one function get_version, and use it for printing...
@ArthurZucker thank you for review, I fixed code style CI related issue, but I have no idea about flax tests (I do not think that it is some how related...
@openvino-book according to this issue on hf hub, you need to upgrade transformers for loading llama3.1 https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct/discussions/15
@brmarkus that is not true that GPU can not be selected, this is just current widget state with saved output because notebook was executed on machine without GPU, NPU if...
No, this transfrmation pass is workaround for some plugin issue used in rag notebook for making embeddings model more npu friendly, it can not be treated as general solution. Unfortunatly,...