DAMO-NLP-SG / DAMO-NLP-SG/Video-LLaMA

如何提升下游任务上finetune的效果

Open
#147 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
3.1k
Forks
286
PR merge metrics
No merged PRs in 30d

Description

您好,请问按照给定的config在下游任务上进行Finetune效果不太好可能是什么原因?是否需要引入lora等方式增加可学习参数的数量以提升模型在下游任务上的效果呢?
感谢您的解答!

Contributor guide

No contributing guide indexed for this repository

Research direction

No files, tests, or entry points are named. Start by locating the downstream fine-tuning configuration and training entry point, then reproduce the reported result with the given config. Done would require a documented diagnosis of the poor effect and an agreed scope for evaluating whether LoRA or another parameter-efficient method is appropriate.

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
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.