Skip to content

Issues: lyogavin/airllm

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

82 Open 79 Closed
82 Open 79 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

B70 need
#182 opened Sep 13, 2024 by ayttop
How to set system prompt
#181 opened Sep 2, 2024 by OKHand-Zy
1
unsloth/Meta-Llama-3.1-405B-Instruct-bnb-4bit
#180 opened Sep 1, 2024 by kendiyang
2
delete_original
#179 opened Aug 31, 2024 by ayttop
4
RuntimeError: shape '[1, 5, 8, 128]' is invalid for input of size 10240 LLama 405B 4-bit on Layer 1
#178 opened Aug 31, 2024 by TitleOS
3
Compression does not work with MLX / Apple Silicon
#177 opened Aug 28, 2024 by sammcj
CUDA Out of memory RTX 4060TI 16G
#175 opened Aug 23, 2024 by 1272870698
RuntimeError: shape '[1, 13, 8, 128]' is invalid for input of size 26624
#172 opened Aug 14, 2024 by zhuojun1024
6
how to increase speed of inference
#166 opened Aug 6, 2024 by Tdrinker
1
Position Embedding with Seq > 512
#165 opened Aug 5, 2024 by Codys12
1
Data Parallel across multiple GPUs?
#164 opened Aug 4, 2024 by Codys12
name 'dynamically_import_QuantLinear' is not defined enhancement New feature or request future work
#163 opened Aug 4, 2024 by gyyixr
1
layer_name 在使用前没有被定义
#162 opened Aug 3, 2024 by yjleo17
4
AssertionError: model.safetensors.index.json should exist
#160 opened Aug 2, 2024 by huangyifu
I can’t run llama-3.1-405B-Instruct-bnb-4bit because of a ValueError: rope_scaling must be a dictionary with two fields.
#159 opened Aug 2, 2024 by LCG22
1
can not run llama 3.1 405B
#158 opened Aug 2, 2024 by taozhiyuai
2
AttributeError: 'AirLLMLlama2' object has no attribute '_supports_cache_class'
#156 opened Jul 18, 2024 by Source61
2
Ramdisk
#155 opened Jul 12, 2024 by HennethAnnun
how to use Qwen2-72B-instuct
#154 opened Jul 10, 2024 by shenhai-ran
2
AssertionError: Torch not compiled with CUDA enabled
#153 opened Jul 4, 2024 by smartdawg
1
No english readme for rlhf
#151 opened Jun 26, 2024 by drawnwren
AttributeError: 'list' object has no attribute 'absmax' when I load Qwen-72B-Chat with 8-bit compression with AirLLMQWen
#149 opened Jun 17, 2024 by Yang-bug-star
I want to use in-context learning in qwen1.5-72b-chat inference and thus use tokenizer.apply_chat_template as in the official tutorial, however ValueError: max() arg. Doesn't airllm support the official inference way ?
#148 opened Jun 16, 2024 by Yang-bug-star
Add support for Mistral model inference
#146 opened Jun 14, 2024 by kunling-cxk
Linear(in_features=28672, out_features=8192, bias=False) does not have a parameter or a buffer named qweight.
#144 opened May 31, 2024 by luzacao
ProTip! Type g i on any issue or pull request to go back to the issue listing page.