Skip to content

Issues: FMInference/H2O

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

31 Open 8 Closed
31 Open 8 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

How to reproduce the result of infinite-length inputs?
#47 opened Dec 3, 2024 by shuhao02
For model generation，I fail with ERROR:KeyError: 'Cache only has 0 layers, attempted to access layer with index 0'
#45 opened Aug 29, 2024 by liyanboSustech
For HELM testing, is an API, like togetherApiKey, necessary?
#44 opened Aug 19, 2024 by DOG-wooooof
TypeError: forward() got an unexpected keyword argument 'cache_position'
#42 opened Jul 25, 2024 by benja-matic
4
ModuleNotFoundError: No module named 'streaming_llm'
#40 opened Jul 25, 2024 by benja-matic
1
Undefined functions
#39 opened Jul 24, 2024 by XdertodX
Current transformers version v4.40 is not supported
#38 opened Jul 16, 2024 by maxjeblick
Evaluation on discrimative datasets with short prompt.
#37 opened Jun 24, 2024 by yinwangsong
Question about the reproduction of COPA results
#36 opened Jun 19, 2024 by hyeseongshin
Recent Budget Simulation is incorrect
#35 opened Jun 13, 2024 by gopikrishnajha
Eviction doesn't happen at all if recent_budget=0
#33 opened Jun 12, 2024 by foreverpiano
No support of GQA of Llama in real_drop
#32 opened May 27, 2024 by Tomorrowdawn
1
The setting of experiments
#31 opened May 22, 2024 by YingYellow
Where is the streaming_utils
#30 opened Apr 28, 2024 by gawainx
1
Supporting new versions of transformers & batch size > 1
#29 opened Apr 23, 2024 by huangyuxiang03
KeyError: 'Cache only has 0 layers, attempted to access layer with index 0'
#25 opened Apr 2, 2024 by hasanar1f
3
Can not reproduce results by LLAMA-7B on OpenBook QA
#24 opened Mar 25, 2024 by AkideLiu
9
Replication of results with h2o_flexgen flex_opt.py
#23 opened Mar 13, 2024 by g-x-w
1
Is the flash attention version ready now?
#21 opened Feb 28, 2024 by York-Cheung
Question about the reproduction of XSUM results
#20 opened Feb 3, 2024 by SherrySwift
14
Package Error when I reproduce as https://github.com/FMInference/H2O/tree/main/h2o_hf
#19 opened Jan 11, 2024 by KylinC
4
About flash attention
#18 opened Jan 10, 2024 by imh966
TASK=xsum HH_SIZE=256 RECENT_SIZE=256 Model=llama-7b and the rouge2 of h2o is low
#17 opened Jan 3, 2024 by duyuxuan1486
3
Error with running run_xsum_flexgen.py
#15 opened Dec 21, 2023 by gushu333
HH scores summed along batch dimension
#14 opened Dec 20, 2023 by yeoedward
4
ProTip! Exclude everything labeled bug with -label:bug.