sample-for-multi-modal-document-to-json-with-sagemaker-ai

Public

This open-source project delivers a complete pipeline for converting multi-page documents (PDFs/images) into structured JSON using Vision LLMs on Amazon SageMaker. The solution leverages the SWIFT Framework to fine-tune models specifically for document understanding tasks.

aws document-processing fine-tuning huggingface idp llama multimodal qwen2-vl sagemaker sft

Creat：2025-02-13T05:30:16

Update：2025-03-23T00:50:23

Stars

Stars Increase

Related projects

Transformers

Hot

bert

? Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

147733

2年前

+59today

Comfyui

Hot

ComfyUI docker images for use in GPU cloud and local environments. Includes AI-Dock base for authentication and improved user experience.

84059

4个月前

+113today

Opencv

c-plus-plus

Open Source Computer Vision Library

83328

7年前

+24today

D2l Zh

book

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

71230

4个月前

+41today

LLaMA Factory

Hot

agent

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

55318

4个月前

+85today

Serverless

aws

? Serverless Framework – Effortlessly build apps that auto-scale, incur zero costs when idle, and require minimal maintenance using AWS Lambda and other managed cloud services.

46811

1年前

+1today