Explore the process of building a Grammar Error Correction (GEC) model using OpenVino quantization techniques in this 55-minute video tutorial. Learn to construct a two-component model featuring a Roberta Base error detector trained with the CoLa Dataset and a Flan-T5 large Grammar correction component fine-tuned with the JFLEG Dataset. Convert both components to IR OpenVino format and quantize the correction component for optimized performance. Gain hands-on experience in implementing CPU inference and access the accompanying notebook for practical application. Enhance your skills in MLOps, data science, and machine learning through this comprehensive demonstration of creating an efficient grammatical error correction pipeline.
MLOps: OpenVino Quantized Pipeline for Grammatical Error Correction
The Machine Learning Engineer via YouTube
Overview
Syllabus
MLOps: OpenVino Quantized Pipeline Gramatical Error Correction #datascience #machinelearning
Taught by
The Machine Learning Engineer
Related Courses
-
Fine-tuning Flan-T5 for Text Classification with MLFlow
-
Fine-tuning Flan-T5 for Sequence-to-Sequence Classification with MLFlow
-
MLOps: Optimización PEFT para Resumen de Diálogos con Flan-T5 (LoRA) - Español
-
MLOps MLFlow: Fine-tuning Flan-T5 for Sequence-to-Sequence Classification in Spanish
-
Fine-tuning Flan-T5 for Text Classification Using MLFlow - Spanish Tutorial
-
MLOPS LLMs: Converting Microsoft Phi3 to GGUF Format with LLaMA.cpp
