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

528 Open 518 Closed
528 Open 518 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

Unsloth for models that are not currently supported
#1338 opened Nov 25, 2024 by scigeek72
Will using Unsloth affect the training results, or does it only serve to accelerate the process?
#1337 opened Nov 25, 2024 by lichaoahcil
[Issue] Triton Compilation Error in Unsloth Fine-Tuning Script on Kernel 5.4.0
#1336 opened Nov 25, 2024 by gityeop
5
GETTING ERROR WHILE RUNNING A KAGGLE NOTEBOOK
#1335 opened Nov 25, 2024 by MuhammadBilal848
3
Issue training with Qwen 2.5 7B
#1333 opened Nov 24, 2024 by Vital1162
4
how to use multiGPU?
#1332 opened Nov 24, 2024 by Zuozhuo
1
Can we use a custom chat template (or no template at all) for vision fine-tuning?
#1331 opened Nov 24, 2024 by Any-Winter-4079
1
add generation prompt enforcement is too severe currently fixing Am fixing now!
#1330 opened Nov 24, 2024 by RonanKMcGovern
3
Fail to Load LoRA Model for VLM Fine-Tune currently fixing Am fixing now! URGENT BUG Urgent bug
#1329 opened Nov 23, 2024 by krittaprot
1
Running into this issue randomly: ImportError: Unsloth: Cannot import unsloth_compiled_cache/Conv3d.py currently fixing Am fixing now! URGENT BUG Urgent bug
#1328 opened Nov 22, 2024 by saum7800
4
[Urgent] After reinstalling unsloth, Llama 3.2/3.1 fine tuning gets error with customized compute_metrics function currently fixing Am fixing now! URGENT BUG Urgent bug
#1327 opened Nov 22, 2024 by yuan-xia
6
qwen2-vl 2b 4-bit always getting OOM, yet llama3.2 11b works!
#1326 opened Nov 22, 2024 by mehamednews
1
Llama 3.2 vision finetuning error (Unsupported: hasattr ConstDictVariable to) currently fixing Am fixing now! URGENT BUG Urgent bug
#1325 opened Nov 22, 2024 by adi7820
2
Unsloth Phi-3.5 LoRA: 3x the Number of Trainable Parameters with the Same Hyperparameters
#1324 opened Nov 22, 2024 by KristianMoellmann
2
Saving the model with save_pretrained_merged failed. currently fixing Am fixing now!
#1323 opened Nov 22, 2024 by WATCHARAPHON6912
1
Loading a vision lora fails with ValueError: Unrecognized model in lora_model. Should have a model_type key in its config.json currently fixing Am fixing now! URGENT BUG Urgent bug
#1322 opened Nov 22, 2024 by saum7800
3
5 times slower then before
#1321 opened Nov 22, 2024 by SidneyLann
4
How to train only last few layers using FastLanguageModel
#1320 opened Nov 22, 2024 by gneeraj97
2
How to fine-tune LLaMA 3.2 11B Vision using LoRA with the recent update?
#1319 opened Nov 21, 2024 by yukiarimo
5
failed finetune qwen32b_awq_int4 using lora with llama-factory
#1314 opened Nov 21, 2024 by Daya-Jin
5
ImportError when importing FastLanguageModel from unsloth
#1313 opened Nov 21, 2024 by MurphyJUAN
4
The tokenizer does not have a {% if add_generation_prompt %}
#1312 opened Nov 21, 2024 by Galaxy-Husky
3
Not able to load model from huggingface repo with correct path (FileNotFoundError: invalid repository id)
#1311 opened Nov 20, 2024 by ygl1020
1
what was the quantisation algorithm used in unsloth/Llama-3.2-1B-bnb-4bit?
#1310 opened Nov 20, 2024 by jayakommuru
1
Does tensorRT-LLM support serving 4bit quantised unsloth Llama model
#1309 opened Nov 20, 2024 by jayakommuru
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.