Skip to content

Issues: texttron/tevatron

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

Clear current search query, filters, and sorts
37 Open 62 Closed
37 Open 62 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

Trainer compute_loss signature mismatch with newer transformers version
#159 opened Nov 4, 2024 by maxjeblick updated Nov 26, 2024
3
unable to train
#131 opened Jun 18, 2024 by riyajatar37003 updated Nov 21, 2024
3
Correctness of "counter average weight reduction"
#143 opened Aug 2, 2024 by rgdyy updated Oct 26, 2024
2
Add __init__.py files to driver folders
#156 opened Oct 16, 2024 by ryan-burt updated Oct 16, 2024
Reproducing repllama on passage retrieval.
#152 opened Sep 19, 2024 by hengran updated Sep 28, 2024
4
load the model erro
#141 opened Jul 30, 2024 by hengran updated Sep 20, 2024
2
Reproducing repllama on document retrieval
#151 opened Sep 9, 2024 by hengran updated Sep 19, 2024
3
evaluating sparse retrievers splade++ (main branch)
#149 opened Sep 3, 2024 by srikanthmalla updated Sep 4, 2024
1
MLLM support
#142 opened Aug 2, 2024 by ChingKwanCheung updated Aug 12, 2024
4
Splade is unavailable
#145 opened Aug 9, 2024 by Swknight updated Aug 12, 2024
1
unable to train
#134 opened Jun 22, 2024 by riyajatar37003 updated Aug 5, 2024
3
Question about training procedure of retriever
#140 opened Jul 29, 2024 by dayuyang1999 updated Jul 30, 2024
2
why the target_label is 0 for all training dataset?
#139 opened Jul 6, 2024 by hecongqing updated Jul 12, 2024
1
Incorrect training steps for distributed setting
#137 opened Jun 30, 2024 by theyorubayesian updated Jun 30, 2024
About RepLLaMA
#103 opened Jan 11, 2024 by sunxiaojie99 updated Jun 18, 2024
20
training error
#132 opened Jun 18, 2024 by riyajatar37003 updated Jun 18, 2024
train retriever
#116 opened Apr 28, 2024 by chenzhongwu updated Apr 30, 2024
1
Purpose of replace_with_xformers_attention() function
#115 opened Apr 19, 2024 by cramraj8 updated Apr 28, 2024
2
lora finetuning error
#114 opened Apr 8, 2024 by MoYang94 updated Apr 8, 2024
Checkpoint path should be absolute
#111 opened Mar 28, 2024 by bhargav25dave1996 updated Apr 2, 2024
4
NQ's mined hard negatives file hn.json contains more queries (70076) than the original NQ train set (58880)?
#113 opened Mar 30, 2024 by x-zb updated Mar 30, 2024
Train in multi-node multi-card environment
#110 opened Mar 27, 2024 by Atlantic8 updated Mar 28, 2024
2
Issues training with custom dataset
#102 opened Jan 9, 2024 by Tostino updated Jan 9, 2024
how to use other datasets for training
#101 opened Jan 5, 2024 by zhaobinNF updated Jan 8, 2024
1
pyarrow.lib.ArrowNotImplementedError: Unsupported cast from struct<docid: string, title: string, text: string> to null using function cast_null
#100 opened Dec 27, 2023 by yakoobbaba478 updated Dec 27, 2023
ProTip! Follow long discussions with comments:>50.