Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / princeton-nlp/LESS issues and pull requests

#36 - Are these processed data selected by `Llama2-7b`?

Issue - State: open - Opened by cafeii 16 days ago

#35 - Can you provide a validation dataset?

Issue - State: open - Opened by kuang1216 17 days ago

#33 - The issue with the Data Selection Pipeline

Issue - State: open - Opened by kuang1216 24 days ago - 6 comments

#32 - Differences in Model Performance When Reproducing Experiment

Issue - State: open - Opened by fannie1208 25 days ago - 4 comments

#30 - `open_instruct` used in `evaluation/eval/utils.py` is out-of-date

Issue - State: closed - Opened by cafeii about 1 month ago - 2 comments

#29 - RDS baseline?

Issue - State: closed - Opened by hamishivi about 2 months ago - 2 comments

#28 - load the optimizer.bin

Issue - State: closed - Opened by kuang1216 about 2 months ago

#27 - Why does the CSV extracted according to the steps show all the scores as nan?

Issue - State: open - Opened by SsmallSong about 2 months ago - 2 comments

#26 - How to get tydiqa-one-shot.json

Issue - State: closed - Opened by ppalantir 3 months ago

#25 - Discrepancy in Model Performance When Reproducing Experiment

Issue - State: open - Opened by tangzhy 3 months ago - 1 comment

#24 - Question about influence scoring (regarding cosine-similarity)

Issue - State: closed - Opened by DSKSD 3 months ago - 2 comments

#23 - Fix the get_info/grad path in README.md

Pull Request - State: open - Opened by kykim0 4 months ago

#22 - At step1, single GPU works while multiple GPUs get stuck.

Issue - State: open - Opened by timturing 5 months ago - 2 comments

#21 - Questions about the influence value

Issue - State: open - Opened by simplelifetime 5 months ago - 1 comment

#20 - OOM Errors in Step 3.1

Issue - State: closed - Opened by ChangyuChen347 5 months ago - 3 comments

#18 - No optimizer.bin in Step 2

Issue - State: open - Opened by mihara-bot 6 months ago - 3 comments

#16 - Error with fast_jl

Issue - State: closed - Opened by simplelifetime 6 months ago - 1 comment

#15 - a small mistake in the code

Issue - State: closed - Opened by ZZZZZccccc123 6 months ago - 3 comments

#14 - some question about calulate socre？

Issue - State: closed - Opened by smashfan 6 months ago - 1 comment

#12 - Question about accuracy

Issue - State: closed - Opened by fyf3 7 months ago - 1 comment

#11 - tiny typo

Pull Request - State: closed - Opened by kgourgou 7 months ago

#9 - Question about running stage 3 script

Issue - State: closed - Opened by 2003pro 7 months ago - 3 comments

#8 - Fix missing return value

Pull Request - State: closed - Opened by leopoldwhite 8 months ago

#7 - Using Multiple GPUs

Issue - State: closed - Opened by SD325 8 months ago - 3 comments

#6 - data selection results

Issue - State: closed - Opened by wang-debug 8 months ago - 2 comments

#5 - Are samples used for warmup training and gradient calculation the same?

Issue - State: closed - Opened by ZigeW 8 months ago - 1 comment

#3 - A concerned question about adding a new baseline.

Issue - State: closed - Opened by FanqingM 9 months ago - 2 comments

#2 - What if we have the optim states of specific tasks at the beginning?

Issue - State: closed - Opened by suhmily 9 months ago - 2 comments

#1 - Does it support baichuan or chatglm?

Issue - State: closed - Opened by amulil 9 months ago - 2 comments