From f26c81a8641cb94dc5346f0cb54468955fe453f6 Mon Sep 17 00:00:00 2001 From: Lucas Pavanelli Date: Mon, 25 Sep 2023 10:22:15 -0300 Subject: [PATCH] Update user doc and add FineTune Search and LLM functional tests --- docs/user/user_doc.md | 13 ++++++++++--- .../finetune/data/finetune_test_run_data.json | 10 +++++++++- 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/docs/user/user_doc.md b/docs/user/user_doc.md index d7647e0a..a74d92fd 100644 --- a/docs/user/user_doc.md +++ b/docs/user/user_doc.md @@ -174,14 +174,21 @@ Using the aiXplain SDK, you can also onboard your dataset into the aiXplain plat [FineTune](https://aixplain.com/platform/finetune) allows you to customize models by tuning them using your data and enhancing their performance. Set up and start fine-tuning with a few lines of code. Once fine-tuning is complete, the model will be deployed into your assets, ready for you to use. -You can also run this FineTune guide in Google Colab: +For now, we support the following tasks: `translation`, `speech-recognition`, `search` and `text-generation`. We have a guide for each task available on Google Colab: -[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1rVxxZpHzyP4FWn_Rd_j_g8tHU76S3rVT?usp=sharing) +- Translation: + - [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1rVxxZpHzyP4FWn_Rd_j_g8tHU76S3rVT?usp=sharing) +- Speech recognition: + - [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1IwzIKT4li_YZbUHPzlXsugqLz_7g6ov6?usp=sharing) +- Search: + - [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1W56VZuJPm0FilnvEvpo38T92XvZIGDUs?usp=sharing) +- Text generation: + - [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1DeaOalATM2X9h0d7Uw4jOoT36WfB9nsB?usp=sharing) ### Creating a FineTune -You can use the `FinetuneFactory` to create a FineTune object using the SDK. For now, we support the following tasks: `translation` and `speech-recognition`: +You can use the `FinetuneFactory` to create a FineTune object using the SDK. Here we show an example on how to fine-tune a translation model: ```python from aixplain.factories import FinetuneFactory, DatasetFactory, ModelFactory diff --git a/tests/functional/finetune/data/finetune_test_run_data.json b/tests/functional/finetune/data/finetune_test_run_data.json index dd5b520e..928bcc2d 100644 --- a/tests/functional/finetune/data/finetune_test_run_data.json +++ b/tests/functional/finetune/data/finetune_test_run_data.json @@ -3,8 +3,16 @@ "model_id": "60ddefae8d38c51c5885eff7", "dataset_id": "64a81e78ead7e90455bb6aeb" }, - { + { "model_id": "60ddef908d38c51c5885dd1e", "dataset_id": "64a8961aead7e90455bb6b62" + }, + { + "model_id": "6499cc946eb5633de15d82a1", + "dataset_id": "650d9f3c27e15c66add3bbf4" + }, + { + "model_id": "640b517694bf816d35a59125", + "dataset_id": "6501ea64b61fed7fe5976c49" } ] \ No newline at end of file