Philipp Schmid
Philipp Schmid
Is this expected to be merged soon?
Thank you for responding! I saw edgen starting their on fork at https://github.com/edgenai/llama_cpp-rs/tree/main, which is inspired by your work https://github.com/edgenai/llama_cpp-rs/blob/847d4f5d104c23b87a925618027942313badec2c/crates/llama_cpp_sys/build.rs#L8 Maybe we could unify all the rust efforts into a...
@pedro-devv thank you for the respond! So it might make more sense to redirect people than to your bindings if you plan to maintain them and @mdrokz is not having...
Thank you @Ierezell. Normally you don't need to log into the ecr locally this should be done during the deployment. Is the error raised by the docker login or by...
does my python version work for you?
This should work out of the box? Which error do you see? It should be possible to send a payload ```json { "inputs": ["text A", "text B"] } ```
Hello @ninajlu, did you check "See https://us-east-1.console.aws.amazon.com/cloudwatch/home?region=us-east-.... for more information.'"? We also have a dedicated blog post on how to deploy `GPT-J`: https://huggingface.co/blog/gptj-sagemaker
You cannot use LayoutLM for "generative" tasks
Hi Yinghuaguan, unfortunately, it is currently hard coded at this file https://github.com/philschmid/efsync/blob/main/efsync/utils/ec2/ec2_main.py . You could either create a pull request and adjust it by adding it to the config file...
Did you run the exact same code?