AIAT
/

Kiddee-qatable1

Table Question Answering

text-generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Edit model card

license: apache-2.0

Tag

openthaigpt/openthaigpt-1.0.0-13b-chat

Datasets:

(https://huggingface.co/datasets/AIAT/Kiddee-data1234)

language:

th
en

metrics:

accuracy 0.53
response time 2.440

pipeline_tag:

table-question-answering

tags:

OpenthaiGPT-13b
LLMModel

This repository contains code and resources for building a Question Answering (QA) system using the Retrieval-Augmented Generation (RAG) approach with the Language Learning Model (LLM).

Introduction

RAG-QA combines the power of retrieval-based models with generative models to provide accurate and diverse answers to a given question. LLM, a state-of-the-art language model, is used for generation within the RAG framework.

sponser

library_name: adapter-transformers

Downloads last month: 42

Safetensors

Model size

13.1B params

Tensor type

FP16

·

Inference Examples

Table Question Answering

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train AIAT/Kiddee-qatable1

Collection including AIAT/Kiddee-qatable1

SuperAi: Thai Table Question Answering Hackathon models

Models used in final submission model in Super AI Engineer Thai Table Question Answering Hackathon • 7 items • Updated May 5