alibaba / alibaba/ServeGen

Is there any chance to share the workload trace for the fine-tune model?

Open
#1 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
175
Forks
16
PR merge metrics
No merged PRs in 30d

Description

Hello, I'm currently studying on multi-lora inference system and looking for any data about the trace of fine-tune model useage.
The paper said "Its model repository contains over 200 foundation models and thousands of fine-tuned models(Bailian).", so I'm wondering is there any chance that Alibaba can share the workload trace for the fine-tune model?

We appreciate any offers of help and are looking for opportunities for collaboration in industry/academia.

Contributor guide

No contributing guide indexed for this repository

Research direction

The issue names no files, tests, or entry points. Start by clarifying whether a fine-tuned-model workload trace can be shared and what scope or format is needed for the multi-LoRA inference study. Done would be an agreed trace or a maintainer response explaining its availability.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.