-
Notifications
You must be signed in to change notification settings - Fork 501
Issues: google/gemma_pytorch
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Inconsistent 'query_pre_attn_scalar' Setting Between 9B and 27B Models
bug
Something isn't working
stat:awaiting response
Status - Awaiting response from author
#71
opened Jul 17, 2024 by
kiddj
Error when run docker/Dockerfile
stat:awaiting response
Status - Awaiting response from author
type:support
Support issues
#53
opened Apr 1, 2024 by
Cguanqin
How to use gemma for multi-round conversations
stat:awaiting response
Status - Awaiting response from author
type:support
Support issues
#52
opened Mar 26, 2024 by
ranck626
How to save memory when loading weights?
bug
Something isn't working
#51
opened Mar 23, 2024 by
KaneGreen
Unable to reproduce MATH resulst
stat:awaiting internal
Status - Awaiting response from Internal Team
type:support
Support issues
#50
opened Mar 23, 2024 by
wenhuchen
Error when running Gemma inference on GPU
stat:awaiting response
Status - Awaiting response from author
type:support
Support issues
#47
opened Mar 18, 2024 by
LarryHawkingYoung
Is max_position_embeddings=8096 neccessary in 2b model?
type:support
Support issues
#41
opened Mar 8, 2024 by
agiwave
not found weight file
stat:awaiting response
Status - Awaiting response from author
type:support
Support issues
#31
opened Mar 1, 2024 by
Cguanqin
is it possible to convert gemma_pytorch to onnx to tflite?
stat:awaiting response
Status - Awaiting response from author
type:support
Support issues
#30
opened Feb 27, 2024 by
nyadla-sys
After deplyed google/gemma-7b-it, there always is error response.
bug
Something isn't working
#26
opened Feb 26, 2024 by
ydh10002023
Cannot run on v4-16 worker 0 TPU VM: "Failed to get global TPU topology"
type:support
Support issues
#25
opened Feb 26, 2024 by
markusheimerl
Output with higher max_length is repetition of base text
stat:awaiting response
Status - Awaiting response from author
type:support
Support issues
#19
opened Feb 23, 2024 by
azrael05
why some prompt doesn't work, the hidden_states will be nan after GemmaModel.forward
bug
Something isn't working
stat:awaiting response
Status - Awaiting response from author
#10
opened Feb 22, 2024 by
vupjing
how to finetune with gemma model?
stat:awaiting response
Status - Awaiting response from author
type:support
Support issues
#8
opened Feb 22, 2024 by
runningabcd
A web runtime supported version of gemma is really needed and high value
enhancement
New feature or request
#4
opened Feb 22, 2024 by
Zwe1
ProTip!
Updated in the last three days: updated:>2024-09-17.