Shubham

@ahmadmustafaanis the error you are getting is because there's no materializer written for type ``. The code should run if you replace `tf.keras.Sequential` with `tf.keras.Model` since Sequential [inherits](https://www.tensorflow.org/api_docs/python/tf/keras/Sequential) from Model...

@ahmadmustafaanis what version of zenml are you using? I am able to run the pipeline using the following code using zenml 0.13.2. ```python import numpy as np import tensorflow as...

@dnth i didn't face any issue ... i was helping in resolving the issue

@strickvl I have addressed the CI errors. Re: Docs and Testing. I have added docs for the new deployer. I am not sure about using [https://github.com/huggingface/hf-endpoints-emulator](https://github.com/huggingface/hf-endpoints-emulator) repo / package for...

@strickvl Re: CI error and dependencies. `huggingface_hub` dependency is added as part of `hugggingface` integration. According to [docs](https://huggingface.co/docs/huggingface_hub/en/guides/inference_endpoints), the minimal version of `huggingface_hub` package supporting Inference Endpoints API is `v0.19.0`....

@jacobbieker I would be interested in submitting a PR! Do we have a workflow in the works? e.g. from above blog would be using chatops gh action to communicate using...

I am facing the same issue on Nvidia L4 (24 GB VRAM) using `llama-2-7b-chat` (quantized versions). ```bash openllm start llama --model-id meta-llama/Llama-2-7b-chat-hf --device 0 --quantize int8 --verbose ``` I tried...

Correct, sending a curl request after first completes.