Skip to content

Issues: unslothai/unsloth

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

636 Open 606 Closed
636 Open 606 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

Unexpected Behavior After Merging Adapters
#1593 opened Jan 29, 2025 by FOCUSLLM
Trainer Updating Only One Adapter During Fine-Tuning with Multiple Adapters and a Router
#1592 opened Jan 29, 2025 by Hazem-Abbas
How to run DeepSeek-R1 IQ1_S 1.58bit at 140 Token/Sec
#1591 opened Jan 28, 2025 by loretoparisi
6
Training a Vision Model with Text-only Inputs
#1590 opened Jan 28, 2025 by jjhoow
1
Problem Exporting to GGUF
#1589 opened Jan 28, 2025 by ChellShort
2
Unexpected behavior with LLaMA 3.1 8b instruct model after reinstallation of unsloth and libraries
#1588 opened Jan 28, 2025 by andrijafactoryww
1
Add Lucie AI from OpenLLM-France
#1587 opened Jan 28, 2025 by ParisNeo
1
Unsloth vision models merging crashes
#1585 opened Jan 28, 2025 by alkollo
2
Reduction in the number of parameters
#1584 opened Jan 28, 2025 by sri-fiddler
2
Unsloth support Qwen2.5 VL
#1583 opened Jan 28, 2025 by fzyzcjy
2
Did you tested unsloth/phi-4-bnb-4bit model with text generation inference (TGI)
#1582 opened Jan 27, 2025 by farzanehnakhaee70
1
Facing this error while trying to use unsloth's 4bit llama 3.2 vision 11B model for OCR task currently fixing Am fixing now!
#1581 opened Jan 27, 2025 by Pavankurapati03
1
Add support for GRPO feature request Feature request pending on roadmap
#1579 opened Jan 25, 2025 by gagan3012
3
Continual Pretraining: Unexpected Trainable Parameters in PEFT Model currently fixing Am fixing now!
#1578 opened Jan 25, 2025 by kailas711
5
Load an existing model under no Internet condition currently fixing Am fixing now!
#1577 opened Jan 25, 2025 by Taimin
1
Do I have to set do_sample=True to generate different outputs with the same model? The official examples do not have this setting.
#1575 opened Jan 24, 2025 by QygjW
1
torch._dynamo.exc.Unsupported when finetuning QWEN2-VL
#1574 opened Jan 23, 2025 by definitelynotadoge
1
Usage Guidance
#1573 opened Jan 22, 2025 by ekmekovski
2
ImportError: cannot import name 'FastLanguageModel' from partially initialized module 'unsloth' (most likely due to a circular import)
#1571 opened Jan 22, 2025 by js-2024
1
TypeError: 'str' object is not callable error with Llama 3.1 8B instruct model (4 bit quantization)
#1570 opened Jan 21, 2025 by BijanProjects
2
ZeroDivisionError: division by zero
#1568 opened Jan 21, 2025 by thangnv02
2
AttributeError: 'NoneType' object has no attribute 'attn_bias'
#1566 opened Jan 20, 2025 by Bhabuk10
1
Validation of Fine-Tuning and Inference Methods for Multi-Turn Conversations with LLaMA 3.1 8B
#1564 opened Jan 20, 2025 by Kshitiz-Khandel
1
Train with multiple candidate output token?
#1562 opened Jan 19, 2025 by fzyzcjy
2
[Fixing] More finetuning support
#1561 opened Jan 19, 2025 by danielhanchen
5 tasks
2
ProTip! Find all open issues with in progress development work with linked:pr.