Xin Li comments

Results 7 comments of


                                            Xin Li

hugging face demo does not work in my local environment

I think it is because it only supports linux-based OS. Hope the documents can clarify it.

What types of models does the Hugging Face runtime support?

It seems only to support the following types of tasks (all related to language models): - AutoModelForSequenceClassification - AutoModelForQuestionAnswering - AutoModelForTokenClassification - AutoModelForMaskedLM - AutoModelForCausalLM - AutoModelForSeq2SeqLM It does not...

Inference graph can use tranformer?

I use an ensemble node and a switch node. The ensemble node contains three language detectors, which identify the language of the input. The switch node contains several translator, each...

Update Huggingface_Transformers examples for safetensors

How do you manage to solve this? I still don't know how torch-model-archiver works with safetensors.

Exception when using torchserve to deploy hugging face model: java.lang.InterruptedException: null

@mreso This is very strange because I can run it with `.mar` files from other places, but not with the ones I pack myself. I tried using a public .mar...

Inference Graph YAML unformatted

The yaml file in the `inference_graph.go` cannot work, I have tried it. I think it is only for demonstration, but not a real file that follows the api. So to...

Collab version mismatch

> It is a temporary issue in Colab. Please see this ticket: [https://github.com/googlecolab/colabtools/issues/5081](url) When we use "numba -s", it showed the CUDA driver is 12.4 while the CUDA runtime version...