Skip to content

Issues: pytorch/torchtune

v0.4.0 Tracker
#1747 opened Oct 2, 2024 by joecummings
Open
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

181 Open 412 Closed
181 Open 412 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

Error while performing Inference with llama-3.2 3B checkpoint
#1749 opened Oct 3, 2024 by Vattikondadheeraj
2
v0.4.0 Tracker
#1747 opened Oct 2, 2024 by joecummings
Can we support class weight in the CEWithChunkedOutputLoss class enhancement New feature or request
#1746 opened Oct 2, 2024 by ye-jin-shop
@felipemello1
3
saving 70B checkpoint takes 1000s for full finetuning 8GPU better engineering Tasks which help improve eng productivity e.g. building tools, cleaning up code, writing docs discussion Start a discussion
#1735 opened Oct 1, 2024 by felipemello1
Multiple GPU low performance question Further information is requested
#1734 opened Oct 1, 2024 by jetstudio-io
3
update config defaults dataset.packed and log_peak_memory_stats community help wanted We would love the community's help completing this issue
#1732 opened Oct 1, 2024 by felipemello1
fix future warning amp.autocast
#1730 opened Oct 1, 2024 by felipemello1
2
when finetuning pretrained models with lora+chat template, embeddings are not updated
#1725 opened Sep 30, 2024 by felipemello1
improve RoPE embeddings
#1724 opened Sep 30, 2024 by felipemello1
Unsupported Ops in MPS: _upsample_bilinear2d_aa discussion Start a discussion
#1723 opened Sep 30, 2024 by Jack-Khuu
9
v0.3 regression, full_finetune_distributed slower ?
#1718 opened Sep 30, 2024 by Delaunay
3
mistral-nemo support community help wanted We would love the community's help completing this issue enhancement New feature or request
#1716 opened Sep 30, 2024 by win4r
mistral-small support community help wanted We would love the community's help completing this issue enhancement New feature or request
#1715 opened Sep 30, 2024 by win4r
Training is stuck at saving checkpoint for Llama3.2
#1713 opened Sep 29, 2024 by apthagowda97
3
torch.distributed.elastic.multiprocessing.errors.ChildFailedError bug Something isn't working
#1710 opened Sep 29, 2024 by Vattikondadheeraj
9
ConcatDataset allows Packed sub datasets
#1708 opened Sep 28, 2024 by pbontrager
Failing tests on MPS bug Something isn't working
#1707 opened Sep 27, 2024 by SalmanMohammadi
Benchmark multimodal perf improvements with num_workers>1
#1705 opened Sep 27, 2024 by RdoubleA
Create multimodal instruction dataset builder
#1704 opened Sep 27, 2024 by RdoubleA
Make ocrvqa default in the_cauldron_dataset
#1703 opened Sep 27, 2024 by RdoubleA
torchtune quantization has different model output comparing with document
#1701 opened Sep 27, 2024 by elfisworking
1
How can I used the fine-tuned model for inferencing?
#1699 opened Sep 27, 2024 by himanshushukla12
1
Bug when I run on single GPU
#1694 opened Sep 26, 2024 by kailashg26
9
Dev install cannot find bitsandbytes>=0.43.0
#1682 opened Sep 25, 2024 by RdoubleA
1
sphinx deprecation warning
#1677 opened Sep 25, 2024 by felipemello1
ProTip! no:milestone will show everything without a milestone.