Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

InternVL2‑40B模型推理速度非常慢 #804

Open
PengJiazhen408 opened this issue Dec 27, 2024 · 0 comments
Open

InternVL2‑40B模型推理速度非常慢 #804

PengJiazhen408 opened this issue Dec 27, 2024 · 0 comments

Comments

@PengJiazhen408
Copy link

PengJiazhen408 commented Dec 27, 2024

我们使用single-image data来lora微调InternVL2‑40B模型。
训练时,平均每小时处理1100条数据。
但在10个data上做测试时,用model.chat 总共5个小时还没跑完,请问有什么方式可以调优?
以下是chat的代码:
image

generation_config = dict(
num_beams=1,
max_new_tokens=4096,
min_new_tokens=8,
do_sample=False,
temperature=0.0,
)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant