add phi3 test

docs/Explore Algorithms/Language Model/Quickstart - Apply Phi 3 Model with HuggingFace CausalLM.ipynb

@@ -0,0 +1 @@
+{"cells":[{"cell_type":"markdown","source":["# Apply Phi3 model with HuggingFace Causal ML"],"metadata":{"nteract":{"transient":{"deleting":false}}},"id":"7a355394-5b22-4c09-8d4f-9467a2fcfce4"},{"cell_type":"code","source":["chats = [\n","    (1, \"fix grammar: helol mi friend\"),\n","    (2, \"What is SynapseML\"),\n","    (3, \"translate to Spanish: hello\")\n","]\n","\n","chat_df = spark.createDataFrame(chats, [\"row_index\", \"content\"])\n","chat_df.show()"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":9,"statement_ids":[9],"state":"finished","livy_statement_state":"available","session_id":"f9f20cd1-6e11-4d5d-af98-de2812967df7","normalized_state":"finished","queued_time":"2025-01-16T08:53:42.1896565Z","session_start_time":null,"execution_start_time":"2025-01-16T08:57:30.7736916Z","execution_finish_time":"2025-01-16T08:57:36.4798503Z","parent_msg_id":"cbb64197-4d0d-45d0-a577-989e4b75b5dc"},"text/plain":"StatementMeta(, f9f20cd1-6e11-4d5d-af98-de2812967df7, 9, Finished, Available, Finished)"},"metadata":{}},{"output_type":"stream","name":"stdout","text":["+---------+--------------------+\n|row_index|             content|\n+---------+--------------------+\n|        1|fix grammar: helo...|\n|        2|   What is SynapseML|\n|        3|translate to Span...|\n+---------+--------------------+\n\n"]}],"execution_count":3,"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"}},"id":"7e76b540-466f-4ab3-9aa9-da8de5517fc1"},{"cell_type":"code","source":["from synapse.ml.llm.HuggingFaceCausallmTransform import HuggingFaceCausalLM\n","\n","phi3_transformer = (\n","    HuggingFaceCausalLM()\n","    .setModelName(\"microsoft/Phi-3-mini-4k-instruct\")\n","    .setInputCol(\"content\")\n","    .setOutputCol(\"result\")\n","    .setModelParam(max_new_tokens=1000)\n","    .setModelConfig(local_files_only=False, trust_remote_code=True)\n",")\n","result_df = phi3_transformer.transform(chat_df).collect()\n","display(result_df)"],"outputs":[{"output_type":"display_data","data":{"application/vnd.livy.statement-meta+json":{"spark_pool":null,"statement_id":16,"statement_ids":[16],"state":"finished","livy_statement_state":"available","session_id":"f9f20cd1-6e11-4d5d-af98-de2812967df7","normalized_state":"finished","queued_time":"2025-01-16T09:18:13.8675906Z","session_start_time":null,"execution_start_time":"2025-01-16T09:18:14.0532319Z","execution_finish_time":"2025-01-16T09:31:36.5402601Z","parent_msg_id":"fa4ecf40-7132-4f1c-b923-c1a10311a336"},"text/plain":"StatementMeta(, f9f20cd1-6e11-4d5d-af98-de2812967df7, 16, Finished, Available, Finished)"},"metadata":{}},{"output_type":"display_data","data":{"application/vnd.synapse.widget-view+json":{"widget_id":"fc0008a8-6371-4c4d-93f3-b9b533c39f48","widget_type":"Synapse.DataFrame"},"text/plain":"SynapseWidget(Synapse.DataFrame, fc0008a8-6371-4c4d-93f3-b9b533c39f48)"},"metadata":{}}],"execution_count":10,"metadata":{"microsoft":{"language":"python","language_group":"synapse_pyspark"},"collapsed":false},"id":"f8db55d9-b89d-420f-80e9-618041def698"}],"metadata":{"kernel_info":{"name":"synapse_pyspark"},"kernelspec":{"name":"synapse_pyspark","language":"Python","display_name":"Synapse PySpark"},"language_info":{"name":"python"},"microsoft":{"language":"python","language_group":"synapse_pyspark","ms_spell_check":{"ms_spell_check_language":"en"}},"nteract":{"version":"[email protected]"},"spark_compute":{"compute_id":"/trident/default","session_options":{"conf":{"spark.synapse.nbs.session.timeout":"1200000"}}},"synapse_widget":{"version":"0.1","state":{"fc0008a8-6371-4c4d-93f3-b9b533c39f48":{"type":"Synapse.DataFrame","sync_state":{"table":{"rows":[{"0":"1","1":"fix grammar: helol mi friend","2":"Hello, my friend."},{"0":"2","1":"What is SynapseML","2":"SynapseML is an open-source machine learning platform that enables users to build, train, and deploy machine learning models using Apache Spark. It provides a unified API for various machine learning algorithms and supports integration with other Spark components. SynapseML simplifies the process of creating machine learning pipelines, making it accessible to data scientists and engineers who are familiar with Spark."},{"0":"3","1":"translate to Spanish: hello","2":"Hola"}],"schema":[{"key":"0","name":"row_index","type":"bigint"},{"key":"1","name":"content","type":"string"},{"key":"2","name":"result","type":"string"}],"truncated":false},"isSummary":false,"language":"scala","wranglerEntryContext":null},"persist_state":{"view":{"type":"details","tableOptions":{},"chartOptions":{"chartType":"bar","categoryFieldKeys":["1"],"seriesFieldKeys":["1"],"aggregationType":"count","isStacked":false,"binsNumber":10,"wordFrequency":"-1","evaluatesOverAllRecords":false},"viewOptionsGroup":[{"tabItems":[{"type":"table","name":"Table","key":"0","options":{}}]}]}}}}},"dependencies":{"lakehouse":{"default_lakehouse":"cf3f397e-6a87-43ab-b8e0-bb9342e11c7a","default_lakehouse_name":"jessiwang_phi3","default_lakehouse_workspace_id":"4751a5bb-6a44-4164-8b31-c3b6a4cf1f8d"}}},"nbformat":4,"nbformat_minor":5}