Skip to content

Issues: Lightning-AI/lit-llama

Looking for LLaMA 2?
#452 opened Aug 25, 2023 by carmocca
Open 3
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

108 Open 162 Closed
108 Open 162 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

fine-tuning time compute
#492 opened Oct 15, 2024 by SKcaiji
add special token
#490 opened Jul 2, 2024 by shunlinlu
Where is tokenizer.model? tokenizer path
#488 opened Apr 24, 2024 by andreamigliorati
1
Using llama3 through lit lama
#487 opened Apr 22, 2024 by fireyanci
5
How to convert lit-llama pretrained model to HF format?
#486 opened Apr 16, 2024 by karkeranikitha
1
why cannot the generate function be used twice
#485 opened Apr 2, 2024 by WyGongya
Converting from lit-llama to HF checkpoint?
#484 opened Mar 24, 2024 by jacqueline-he
it seems that hash of traindata is lost, so it's impossible to continue finetune after stop
#483 opened Mar 16, 2024 by drazdra
PackedDatasetBuilder does not separate with sep_token
#482 opened Mar 6, 2024 by calvintwr
Beam search generation
#477 opened Dec 27, 2023 by hellowoe23
Error: git submodule update --init --recursive -q did not run successfully
#475 opened Dec 14, 2023 by seupedro
1
Ban some tokens
#474 opened Nov 22, 2023 by AnnaKholkina
Can I use Lightning fabirc to pre train llama2 on v100?
#473 opened Nov 17, 2023 by JerryDaHeLian
1
RuntimeError: Expected x1.dtype() == cos.dtype() to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.)
#472 opened Nov 17, 2023 by JerryDaHeLian
1
How to quantize LLama in fine-tuning ?
#470 opened Nov 13, 2023 by sfarzi
How to convert hf weight of 70b to lit-lamma weights?
#469 opened Nov 10, 2023 by sfarzi
RuntimeError: probability tensor contains either inf, nan or element < 0
#467 opened Nov 2, 2023 by AI-Zebra
Why is LLaMA response to queries in the conversation so wrong?
#466 opened Oct 31, 2023 by Harsh-raj
[question] nan loss value and run time error
#463 opened Oct 28, 2023 by nevermet
[question] assert lora_path.is_file() error
#462 opened Oct 23, 2023 by nevermet
1
Question about 'validating...' from lora.py
#461 opened Oct 21, 2023 by nevermet
[question] error message while finetuning
#460 opened Oct 21, 2023 by nevermet
2
Adapter finetuning do not run on two cards (A100 40G)
#459 opened Oct 2, 2023 by wasifferoze
Mistral Model
#458 opened Oct 1, 2023 by PierreColombo
1
When I finetuned the model, an error occurred during the decoding process: IndexError: Out of range: piece id is out of range.
#457 opened Sep 30, 2023 by HypherX
ProTip! Exclude everything labeled bug with -label:bug.