Skip to content

Issues: meta-llama/llama

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
414 Open 642 Closed
414 Open 642 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

rotary position embedding cause different output in different tensor parallel settings! model-usage issues related to how models are used/loaded
#203 opened Mar 16, 2023 by marscrazy
1
How to load multiple GPU version without torchrun documentation Improvements or additions to documentation model-usage issues related to how models are used/loaded
#84 opened Mar 3, 2023 by ruian0
8
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9) compatibility issues arising from specific hardware or system configs documentation Improvements or additions to documentation
#93 opened Mar 3, 2023 by hopto-dot
21
Unable to run example.py compatibility issues arising from specific hardware or system configs
#98 opened Mar 4, 2023 by jessebikman
9
does anyone did with a single RTX 3070 Ti 8Gb? model-usage issues related to how models are used/loaded
#145 opened Mar 7, 2023 by felipehime
7
Sentence/ Word embedding from LLaMA new-feature New feature or request
#152 opened Mar 8, 2023 by kmukeshreddy
8
2 process started but the model loaded only on one device? model-usage issues related to how models are used/loaded
#172 opened Mar 10, 2023 by minlik
Run 65B on 2PC with 4 GPU each, distribution inference failed model-usage issues related to how models are used/loaded
#173 opened Mar 10, 2023 by sophieyl820
Distributing LLaMA on multiple machines within the same network community-discussion
#176 opened Mar 10, 2023 by fabawi
5
Plain pytorch LLaMA implementation (no fairscale, use as many GPUs as you want) feedback-blogpost If the issue or fix has potential for broader announcement and blog post. model-usage issues related to how models are used/loaded
#179 opened Mar 11, 2023 by galatolofederico
8
How to recreate Winogrande results documentation Improvements or additions to documentation
#188 opened Mar 13, 2023 by DanielWe2
Can not reproduce the results on the paper with 65B ckpt? model-usage issues related to how models are used/loaded
#193 opened Mar 13, 2023 by Ageliss
1
Able to load 13B model on 2x3090 24Gb! But not inference... :( compatibility issues arising from specific hardware or system configs documentation Improvements or additions to documentation
#61 opened Mar 2, 2023 by carlos-gemmell
15
Stuck when I run inference needs-more-information Issue is not fully clear to be acted upon
#194 opened Mar 13, 2023 by BeachWang
3
run example.py error model-usage issues related to how models are used/loaded
#205 opened Mar 16, 2023 by coderabbit214
1
It would be immensely useful to have an example that can be run in a notebook documentation Improvements or additions to documentation
#206 opened Mar 16, 2023 by vigna
1
New AI copyright laws says weights aren't covered?? miscellaneous does not fit an existing category, useful to determine whether we need further categorization question General questions about using Llama2
#207 opened Mar 17, 2023 by elephantpanda
Will the evaluation code release? documentation Improvements or additions to documentation research-paper Issues and questions relating to the published architecture or methodology
#211 opened Mar 17, 2023 by lshowway
15
Multi-GPU models give bizarre results on example.py model-usage issues related to how models are used/loaded
#212 opened Mar 18, 2023 by tbenst
2
BBH stats? documentation Improvements or additions to documentation research-paper Issues and questions relating to the published architecture or methodology
#214 opened Mar 18, 2023 by i-am-neo
My link expired for downloading model files and tokenizer. how can i request it back ? model-access issues and questions related to accessing the model, application form
#215 opened Mar 18, 2023 by raghav20
2
Unable to reproduce the HumanEval performance, very poor performance performance Runtime / memory / accuracy performance issues research-paper Issues and questions relating to the published architecture or methodology
#223 opened Mar 21, 2023 by sairitwik27
3
Guidance on releasing the fine-tuned LLaMA model weights legal potential legal/licensing inquiries
#226 opened Mar 22, 2023 by binmakeswell
1
multi GPU error model-usage issues related to how models are used/loaded
#228 opened Mar 22, 2023 by yuxuan2015
3
00212621435547
#1309 opened Dec 25, 2024 by aoukas21435547
3
ProTip! Type g i on any issue or pull request to go back to the issue listing page.