# LLM Inference with CTranslate2 on SageMaker This project contains sample Notebooks to deploy Large Language Models (LLMs) optimized for inference using CTranslate2 on SageMaker. ## List of Notebooks | Noteobok | Description | | -------- | ----------- | | [CTranslate2/OpenCALM_Inference_ja.ipynb](CTranslate2/OpenCALM_Inference_ja.ipynb) | Deploying Pre-trained OpenCALM with CTranslate2 for faster inference | | [CTranslate2/OpenCALM_LoRA_ja.ipynb](CTranslate2/OpenCALM_LoRA_ja.ipynb) | Deploying OpenCALM LoRA with CTranslate2 for faster inference | | [CTranslate2/Rinna_Neox_Inference_ja.ipynb](CTranslate2/Rinna_Neox_Inference_ja.ipynb) | Deploying Rinna NeoX with CTranslate2 for faster inference | | [CTranslate2/Rinna_Neox_LoRA_ja.ipynb](CTranslate2/Rinna_Neox_LoRA_ja.ipynb) | Deploy Rinna NeoX LoRA with CTranslate2 for faster inference |