rkoystart
rkoystart
@Taka152, thanks for your response. This is the `export/hf_bart_export.py` ``` """ Export Hugging Face BART models to protobuf/hdf5 format. """ import os from collections import OrderedDict import tensorflow as tf...
I have 2 doubts 1) apart from `nvcc fatal : Unsupported gpu architecture 'compute_86'` it is also saying `RuntimeError: Error building extension 'lightseq_layers'`. Is it also because of the torch...
Hi @guillaumekln the suggested solution has fixed the issue. But can i know what was the root cause of the issue and how the suggested solution fixes it.
Hi @guillaumekln , only after setting both the flags I am getting proper output. >What CTranslate2 version are you using? The ctranslate version i am using is 2.12.0 >Did you...
Not yet, have not resolved it @LouisAI-DL Not sure what is causing the issue exactly
@wwyx88 could not resolve it. waiting for some suggestion from the authors
@honnibal I have a model trained in Allen nlp 0.9.0 and it depends on this version of spacy. All these dependencies are moved to production. That is why I am...
i have tried a small workaround for the above error: 1) converted the storageview object of type `bfloat16` obtained as the output from the `forward_batch` function to `float16` using `.to(ctranslate2.DataType.float16)`...
@guillaumekln any help or suggestions from your side ?