Skip to content

Issues: xlang-ai/instructor-embedding

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

32 Open 78 Closed
32 Open 78 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

TypeError: _load_sbert_model() received unexpected keyword argument 'token' when initializing INSTRUCTOR model in Colab Notebook
#125 opened Sep 11, 2024 by devin-liu
4
correct quantization in readme
#124 opened Aug 12, 2024 by BBC-Esq
prompt parameters cannot be used?
#123 opened Jul 24, 2024 by Huangouzm
1
NameError: name 'disabled_tqdm' is not defined
#121 opened Jul 8, 2024 by marybloodyzz
1
set sentence_transformer =2.6.0
#120 opened Jul 2, 2024 by Soberaice
2
in kaggle
#119 opened Jul 1, 2024 by Soberaice
1
Redundant code & Tokenize issue
#118 opened Jun 3, 2024 by JonathanZha47
3
Some weights of the model checkpoint at /home/rnd/wmj/instructor-large/instructor-embedding/output/checkpoint-6500/ were not used when initializing T5EncoderModel: ['2.linear.weight'] - This IS expected if you are initializing T5EncoderModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). - This IS NOT expected if you are initializing T5EncoderModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). max_seq_length 512
#117 opened May 11, 2024 by EricPaul03
Fine-tune cross- encoder by "Instruction-Finetuned Text"
#114 opened Apr 17, 2024 by QuangTQV
Chinese support?
#110 opened Feb 27, 2024 by Yaqing2023
1
Improving inference time
#109 opened Feb 15, 2024 by alokpadhi
2
Phrase embeddings in context
#108 opened Feb 12, 2024 by jnferfer
2
Discrepancy in training data versions
#107 opened Jan 30, 2024 by vaibhavad
Model not loading
#106 opened Jan 29, 2024 by laylabitar
7
Are these embeddings Contextualized Embeddings ?
#103 opened Dec 26, 2023 by jbdatascience
1
KeyError task_name
#101 opened Dec 20, 2023 by zanussbaum
3
Save and load dynamically quantized model
#99 opened Nov 16, 2023 by roman-dobrov
4
Why I cannot save model?
#97 opened Nov 14, 2023 by txye
3
Inconsistency between the instruction template suggested vs that in the training data
#96 opened Nov 9, 2023 by debraj135
5
Production Level Updates
#93 opened Oct 26, 2023 by Nicholas-Schaub
2
Issue with Evaluation ArguAna
#89 opened Oct 3, 2023 by yeliusf
5
How the training data is divided？
#87 opened Sep 27, 2023 by wsa-dhu
4
Runtime Optimization
#86 opened Sep 25, 2023 by aditya-y47
1
You script to quantize the instructor models simply doesn't work.
#85 opened Sep 17, 2023 by BBC-Esq
7
Inference using TensorRT
#81 opened Aug 24, 2023 by mon28
1
ProTip! Updated in the last three days: updated:>2024-11-12.