[go: nahoru, domu]
Skip to content

Issues: unslothai/unsloth

Conda installation instructions
#250 by danielhanchen was closed Mar 17, 2024
Closed 5
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
357 Open 216 Closed
357 Open 216 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/codegemma-2b-bnb-4bit: Model Error when Setting max_seq_length > 8192 fixed - pending confirmation Fixed, waiting for confirmation from poster
#584 opened Jun 4, 2024 by terraformmachine
5
Using custom Llama-3 tokenizer
#607 opened Jun 7, 2024 by MikeMpapa
1
Batch size
#606 opened Jun 7, 2024 by nichellehouston
1
Epoch Number
#605 opened Jun 7, 2024 by nichellehouston
1
Training on instructions
#603 opened Jun 7, 2024 by Oseltamivir
1
2
Error message when using ORPO fine-tuning
#601 opened Jun 6, 2024 by MRQJsfhf
1
Mistral fine-tuning resume error.
#600 opened Jun 6, 2024 by duynt575
10
Buffer is not null terminated!
#598 opened Jun 6, 2024 by happy1wawayu
3
How load Loar from Hugging Face ?
#596 opened Jun 6, 2024 by a442509097
4
Unable to save and then load the local saved trained model
#595 opened Jun 5, 2024 by dynamite9999
3
TypeError: '<' not supported between instances of 'str' and 'int' when load unsloth/mistral-7b-instruct-v0.2 currently fixing Am fixing now!
#589 opened Jun 5, 2024 by hanifabd
7
load_in_4bit should be False by default.
#588 opened Jun 4, 2024 by ronakk-google
3
will it work on arm (aarch64) ?
#587 opened Jun 4, 2024 by zoldaten
1
Can I train ollama3 without GPU?
#565 opened May 30, 2024 by msft2000
6
Triton 3.0.0 does not work currently fixing Am fixing now!
#583 opened Jun 3, 2024 by jhu960213
4
defining your own quantization_config fails
#581 opened Jun 3, 2024 by d23845jg
6
Quantization error - model.save_pretrained_gguf(new_model, tokenizer, quantization_method = "q4_k_m")
#579 opened Jun 2, 2024 by dynamite9999
6
error inference currently fixing Am fixing now!
#576 opened Jun 2, 2024 by gabzitto
3
NotImplementedError: Unsloth: microsoft/Phi-3-medium-128k-instruct not supported yet!
#574 opened Jun 1, 2024 by yimingqian
1
NotImplementedError: Unsloth: CohereForAI/c4ai-command-r-v01 not supported yet!
#573 opened Jun 1, 2024 by yimingqian
3
How to quantasize cogvlm2 image understanding model
#572 opened May 31, 2024 by Dineshkumar-Anandan-ZS0367
3
Gemma 7B IT prompt formatting query
#571 opened May 31, 2024 by AvisP
3
raise RuntimeError("mmap can only be used with files saved with "
#570 opened May 31, 2024 by v-yunbin
5
Possible CrossEntropy optimization currently fixing Am fixing now!
#569 opened May 31, 2024 by dragosconst
1
NameError: name 'FastLanguageModel' is not defined
#567 opened May 31, 2024 by Jackiexiong
1
ProTip! Updated in the last three days: updated:>2024-07-06.