kubeedge/ianvs

Clarification needed for dataset usage in example / llm_simple_qa .

Open

#233 opened on Aug 6, 2025

View on GitHub
 (2 comments) (0 reactions) (1 assignee)Python (168 forks)auto 404
good first issuekind/cleanupkind/documentation

Repository metrics

Stars
 (178 stars)
PR merge metrics
 (PR metrics pending)

Description

Introduction or background of this discussion: Ianvs includes a wide range of examples showcasing its benchmarking capabilities. As far as I see , Issue #194 keeps a track of all the issues which are yet to be verified and well documented.

This issue is about the example llm_simple_qa

Contents of this discussion:

I've been trying to run the llm_simple_qa example and encountered some confusion regarding the dataset. The README.md for this example embeds the dataset content directly and asks users to manually copy it. This differs significantly from the cloud-edge-collaborative-inference-for-llm example, which provides a clear kaggle download command for its dataset.

Screenshot of README.md of llm_simple_qa

Problem: Lack of clear documentation and clarify in llm_simple_qa example .In addition , a verification is needed where the example runs or not .

Contributor guide

Research direction
Review the README of the llm simple qa example, compare it with the cloud edge collaborative inference for llm example, find the dataset source, improve documentation with clear acquisition steps, and verify the example runs.
Tech stack
python
Domain
backenddata
Issue type
Documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
GitPython
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70