AMD-SHARK-Studio

mirror of https://github.com/nod-ai/AMD-SHARK-Studio.git synced 2026-02-19 11:56:43 -05:00

Files

Ean Garvey a3654f33da Fix sourcing for canonical MiniLM shark_tank model artifacts. (#278 )

* Fix generation of MiniLM artifacts.

* Fix miniLM output for validation. Xfail numerics failure on mpnet.

* Update distilbert-base-uncased_tf_test.py

* try-except for transition of minilm model

2022-08-17 23:03:47 -05:00

bert_large_gen.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

bert_large_run.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

bert_large_tf.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

bert_small_gen.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

bert_small_run.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

bert_small_tf_run.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

huggingface_MiniLM_gen.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

huggingface_MiniLM_run.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

huggingface_MiniLM_tf.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

README.md

Add seq_classification shark module to run seq_classification

2022-06-14 22:36:19 +05:30

seq_classification.py

Add shark_importer for torch_models. (#183 )

2022-07-12 20:38:19 -07:00

tf_model_list.csv

Fix sourcing for canonical MiniLM shark_tank model artifacts. (#278 )

2022-08-17 23:03:47 -05:00

README.md

Running SharkInference on CPUs, GPUs and MAC.

Run the binary sequence_classification.

The models supported are: hugging face sequence classification

./seq_classification.py --hf_model_name="hf_model" --device="cpu" # Use gpu | vulkan

Once the model is compiled to run on the device mentioned, we can pass in text and get the logits.