Skip to content

Is it possible to increase the Baihuan2-13b default ctx length to 4096? #131

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.

Sign up for GitHub

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

Jump to bottom
Open
trekrollercoaster opened this issue Sep 22, 2023 · 0 comments
Open

Is it possible to increase the Baihuan2-13b default ctx length to 4096? #131

trekrollercoaster opened this issue Sep 22, 2023 · 0 comments

Comments

@trekrollercoaster
Copy link

trekrollercoaster commented Sep 22, 2023 •
edited
Loading

【BUG: CUDA error invalid configuration argument】When token length more than 2048 use Baichuan2-13B-Chat

When using Baichuan2-13B-Chat cpp model and token length more than 2048, will killed by this error:

CUDA error 9 at /tmp/pip-install-alzfik5u/chatglm-cpp_304776c77dfd4f94a8265b20b0fe43e0/third_party/ggml/src/ggml-cuda.cu:6047: invalid configuration argument
@trekrollercoaster trekrollercoaster changed the title 【BUG: CUDA error invalid configuration argument】When token length more than 1000 use Baichuan2-13B-Chat Is it possible to increase the Baihuan2-13b default ctx length to 4096? Sep 25, 2023
@trekrollercoaster trekrollercoaster mentioned this issue Oct 23, 2023
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@trekrollercoaster