DAMO-NLP-SG / DAMO-NLP-SG/Video-LLaMA
如何提升下游任务上finetune的效果
Open
- 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