Skip to content

Issues: jalammar/ecco

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
32 Open 31 Closed
32 Open 31 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

"Predicted tokens" - add visual indication for partial tokens enhancement New feature or request
#5 opened Dec 2, 2020 by jalammar updated Apr 7, 2021
Why do we need to construct one-hot vectors of the input_ids and then multiply by the embeddings, as opposed to applying the embedding directly?
#43 opened Sep 23, 2021 by vgoklani updated Oct 29, 2021
1
Adding AraBERT
#42 opened Aug 16, 2021 by ay94 updated Dec 4, 2021
2
Merge partial tokens in token visualizations [Generation & Attribution]
#51 opened Dec 12, 2021 by jalammar updated Dec 14, 2021
1
Add models to config
#52 opened Dec 12, 2021 by jalammar updated Dec 31, 2021
2 of 3 tasks
Which french model is supported in ecco library
#45 opened Oct 18, 2021 by Ghani-25 updated Jan 12, 2022
5
BART Support
#31 opened Feb 8, 2021 by anshoomehra updated Jan 17, 2022
9
Tokenizer has partial token suffix instead of prefix
#65 opened Jan 19, 2022 by guustfranssensEY updated Jan 20, 2022
1
Remove tokenizer_config usage from the library
#67 opened Jan 23, 2022 by jalammar updated Jan 23, 2022
Add Primary Attribution support for BERT classification help wanted Extra attention is needed
#64 opened Jan 17, 2022 by jalammar updated Jan 25, 2022
4
Running Eccomap for Pre Trained BertForMaskedLM
#70 opened Jan 28, 2022 by iamakshay1 updated Feb 10, 2022
1
Rankings_watch displaying wrong sequence bug Something isn't working
#84 opened Nov 11, 2022 by MiriUll updated Nov 11, 2022
1
Bug: Broken links in docs
#85 opened Nov 25, 2022 by keyboardAnt updated Nov 25, 2022
Request for feature addition: Visualization of Neuron Activations and Clustered Neuron Firings
#93 opened Jun 28, 2023 by cristianestojeda updated Jun 28, 2023
1
bug -object has no attribute 'lm_head'-
#91 opened Jun 6, 2023 by LeonardRanaldi updated Jun 28, 2023
2
Presence of character Ġ before each token in output bug Something isn't working
#87 opened Apr 18, 2023 by osmanii updated Jun 28, 2023
2
I can't find jupyter notebook for Input_Saliency.
#96 opened Jul 18, 2023 by SuperBianC updated Jul 18, 2023
Error encountered when comparing activation matrices in batch generation loop
#97 opened Jul 19, 2023 by miguel-kjh updated Jul 19, 2023
Adding GENRE model to ecco
#94 opened Jun 29, 2023 by sky-2002 updated Jul 21, 2023
1
AttributeError: 'OutputSeq' object has no attribute 'saliency'
#86 opened Dec 5, 2022 by Claus1 updated Jul 31, 2023
4
import ecco ERRO
#88 opened May 15, 2023 by nikipi updated Aug 12, 2023
9
How to add my own model like chinese-bert-wwm-ext
#104 opened Aug 12, 2023 by Myoontyee updated Aug 12, 2023
How to retrieve salience of some specific words?
#105 opened Sep 5, 2023 by CarhoJohn updated Sep 11, 2023
1
llama support
#89 opened May 22, 2023 by srikanthmalla updated Sep 25, 2023
4
Google Colab support only Python 3.10
#102 opened Aug 2, 2023 by Rolkarolka updated Dec 4, 2023
7
ProTip! Exclude everything labeled bug with -label:bug.