Variation error when running the bert base model download script

[anandhu-eng]

command:

cm run script --tags=get,ml-model,raw,bert,bert-base,_int8,_deepsparse

output:

INFO:root:* cm run script "get ml-model raw bert bert-base _int8 _deepsparse"
INFO:root:  * cm run script "get ml-model zoo deepsparse _pruned95_obs_quant-none"

CM error: no scripts were found with above tags and variations

variation tags ['pruned95_obs_quant-none'] are not matching for the found script get-ml-model-neuralmagic-zoo with variations dict_keys(['bert-base-pruned95_obs_quant-none', 'model-stub.zoo:nlp/question_answering/bert-base/pytorch/huggingface/squad/pruned95_obs_quant-none', 'obert-large-pruned95_quant-none-vnni', 'model-stub.zoo:nlp/question_answering/obert-large/pytorch/huggingface/squad/pruned95_quant-none-vnni', 'mobilebert-14layer_pruned50_quant-none-vnni', 'model-stub.zoo:nlp/question_answering/mobilebert-none/pytorch/huggingface/squad/14layer_pruned50_quant-none-vnni', 'mobilebert-base_quant-none', 'model-stub.zoo:nlp/question_answering/mobilebert-none/pytorch/huggingface/squad/base_quant-none', 'mobilebert-none-base-none', 'model-stub.zoo:nlp/question_answering/mobilebert-none/pytorch/huggingface/squad/base-none', 'oberta-base-pruned90-quant-none', 'model-stub.zoo:nlp/question_answering/oberta-base/pytorch/huggingface/squad/pruned90_quant-none', 'roberta-base-pruned85-quant-none', 'model-stub.zoo:nlp/question_answering/roberta-base/pytorch/huggingface/squad/pruned85_quant-none', 'mobilebert-14layer_pruned50-none-vnni', 'model-stub.zoo:nlp/question_answering/mobilebert-none/pytorch/huggingface/squad/14layer_pruned50-none-vnni', 'obert-base-pruned90-none', 'model-stub.zoo:nlp/question_answering/obert-base/pytorch/huggingface/squad/pruned90-none', 'obert-large-pruned97-quant-none', 'model-stub.zoo:nlp/question_answering/obert-large/pytorch/huggingface/squad/pruned97_quant-none', 'bert-base_cased-pruned90-none', 'model-stub.zoo:nlp/question_answering/bert-base_cased/pytorch/huggingface/squad/pruned90-none', 'bert-base-pruned90-none', 'model-stub.zoo:nlp/question_answering/bert-base/pytorch/huggingface/squad/pruned90-none', 'bert-large-pruned80_quant-none-vnni', 'model-stub.zoo:nlp/question_answering/bert-large/pytorch/huggingface/squad/pruned80_quant-none-vnni', 'obert-large-pruned95-none-vnni', 'model-stub.zoo:nlp/question_answering/obert-large/pytorch/huggingface/squad/pruned95-none-vnni', 'obert-large-pruned97-none', 'model-stub.zoo:nlp/question_answering/obert-large/pytorch/huggingface/squad/pruned97-none', 'bert-large-base-none', 'model-stub.zoo:nlp/question_answering/bert-large/pytorch/huggingface/squad/base-none', 'obert-large-base-none', 'model-stub.zoo:nlp/question_answering/obert-large/pytorch/huggingface/squad/base-none', 'model-stub.#'])

[arjunsuresh]

Thank you @anandhu-eng for fixing this issue. It'll be good to list all the 14 variations + the generic model-stub from neural-magic zoo in our docs page for bert,deepsparse.

[anandhu-eng]

Sure @arjunsuresh

[anandhu-eng]

Thank you @anandhu-eng for fixing this issue. It'll be good to list all the 14 variations + the generic model-stub from neural-magic zoo in our docs page for bert,deepsparse.

Hi @arjunsuresh , should we add the cm run script commands for downloading these models? As of now, only official models are listed here.

[arjunsuresh]

No. That page is only for the official ones.

[anandhu-eng]

closing as changes are merged in PR: GATEOverflow/inference#24