open-compass / open-compass/VLMEvalKit
[BUG?] 使用同样的模型,在此 repo下跑推理与模型官方(例如 LLaVA)的推理 demo 结果不同
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 4.4k
- Forks
- 768
- Avg merge
- 1d 10h
- Merged PRs (30d)
- 17
Description
例如:
from vlmeval.config import supported_VLM
model = supported_VLM['llava_v1.5_7b']()
ret = model.generate([{'type': 'image', 'value': '${your_home}/LMUData/images/MME/945.jpg'}, {'type': 'text', 'value': 'This is a picture from a real scene. Is there only two real apples in this picture? Please answer yes or no.'}])
print(ret)
得出来输出为1!似乎看起来 instruction-following 能力很弱 : (
然而,使用 llava 官方提供的 CLI 测试结果输出为 Yes/No!!!
需要注意的是,如果把 Please answer yes or no. 前面仅有一个空格改为两个空格,在本 repo 代码下也能输出 Yes/No???
@kennymckormick 麻烦您帮忙看下是不是有 bug,测试的几个结果不好的似乎都是由于没有按照要求输出,也就是“仅在本 repo”出现的 instruction-following 弱的情况。
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by running the reported supported_VLM['llava_v1.5_7b'] model.generate example with both one and two spaces before the instruction. Compare those outputs with the official LLaVA CLI result, then trace the prompt and generation path used by model.generate. Done means identifying and correcting the repository-specific cause so the same prompt follows the requested Yes/No format.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100