Diego Fiori

Hello @ozayr, once optimized the model you must just save its compiled version, i.e. the content of the variable `model_optimized` in the notebook (alternatively by the end of the notebook...

In addition if you think it could be useful for the rest of the community you can add in speedster/api a utils.py module where you can implement the two functions...

Hello @tobymcclean! Thank you for reporting the error! Could you please share with us the code snippet that generates the error?

Hi @hdnh2006, thank you for the contribution. Happy to assist you and accelerate your model together. We ran again some tests on Yolov5 in [this colab](https://colab.research.google.com/drive/1fB-tZYBEnzSodVpcqZ7t08WQ7K4UKdBH?usp=sharing) and got the following...

Hello @hdnh2006 , On the different performance respect to the Ultralytics implementation I think this can be due to the input your are giving to the `optimize_model` function. In fact,...

With fp16 precision in speedster I am getting 1.187 ms of inference time. I'm waiting for the int8 result.

``` model_optimized = optimize_model( model=core_wrapper, input_data=input_data, optimization_time="unconstrained", metric_drop_ths=0.1 ) ```

Hi @distbit0, uploading the weights on bittorrent would be against the License distributed by Meta for LLaMA's weights. Up-to-date the LLaMA weights can be obtained only using Meta official [google...

This is due to a conflict between the versions of Pip and conda, see [this issue](https://github.com/explosion/spaCy/discussions/9397) for further details. You can solve it uninstalling anaconda and installing the [Arm64 supported...

Hello @ylassoued, thank you very much for reaching out. Re 1: Yes all the steps are required since they reflect the three training steps used for ChatGPT (InstructGPT-like models). *...