Skip to content

Issues: predibase/lorax

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
139 Open 120 Closed
139 Open 120 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

Project Roadmap enhancement New feature or request
#57 opened Nov 22, 2023 by tgaddair
16 of 36 tasks
35
Is there any plan to support dynamic lora for qwen/chatglm models? enhancement New feature or request
#101 opened Dec 5, 2023 by KrisWongz
21
Does lorax currently support GPT2 finetuned adapters? enhancement New feature or request
#84 opened Nov 30, 2023 by abhijithnair1
2 of 4 tasks
19
Improve OpenAI API compatibility
#216 opened Jan 31, 2024 by rbollampally
13
Error while running the pre-built container using Podman question Further information is requested
#266 opened Feb 21, 2024 by chaser06
11
Sample command with mistral-7b failed question Further information is requested
#312 opened Mar 7, 2024 by hayleyhu
2 of 4 tasks
@tgaddair
10
how does this differ from s-Lora? question Further information is requested
#90 opened Nov 30, 2023 by priyankat99
9
Support custom tokenizer when loading a local model bug Something isn't working
#151 opened Dec 25, 2023 by yinjiaoyuan
8
Fails hard on CUDA error
#523 opened Jun 22, 2024 by yunmanger1
2 of 4 tasks
7
decapoda-research/llama-13b-hf is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' question Further information is requested
#310 opened Mar 7, 2024 by sleepwalker2017
7
Llama3-8b-Instruct won't stop generating bug Something isn't working
#442 opened Apr 27, 2024 by ekim322
4 tasks
@tgaddair
6
Using Source = Local for Base Model enhancement New feature or request
#347 opened Mar 20, 2024 by silveranalytics
@magdyksaleh
6
Second GPU is not found when running --sharded true question Further information is requested
#150 opened Dec 24, 2023 by psych0v0yager
2 of 4 tasks
@tgaddair
6
Quantization appears to be broken, at least for AWQ and BnB
#722 opened Dec 21, 2024 by codybum
2 of 4 tasks
5
Can't run Mistral quantized on T4 enhancement New feature or request
#417 opened Apr 16, 2024 by emillykkejensen
2 of 4 tasks
5
Want Lorax with newer version of TGI question Further information is requested
#329 opened Mar 14, 2024 by yangelaboy
5
Issue using adapter with large prompt + sharded bug Something isn't working
#283 opened Feb 26, 2024 by tgaddair
@tgaddair
5
Error deploying GPTQ models to sagemaker
#235 opened Feb 11, 2024 by GlacierPurpleBison
2 of 4 tasks
@geoffreyangus
5
ValueError: Adapter '/data/llama2-lora' is not compatible with model '/data/Llama-2-7b-chat-hf'. Use --model-id '/new-model/llama2-7b/Llama-2-7b-chat-hf' instead. question Further information is requested
#172 opened Jan 10, 2024 by Senna1960321
2 of 4 tasks
5
Latency increase when run on multi-GPU question Further information is requested
#116 opened Dec 8, 2023 by prd-tuong-nguyen
2 of 4 tasks
5
Some error records and questions question Further information is requested
#115 opened Dec 8, 2023 by KrisWongz
1 of 4 tasks
5
Phi 3.5 vision (4B model) enhancement New feature or request
#637 opened Oct 8, 2024 by CheeseAndMeat
2 tasks done
4
Quickstart example not working
#489 opened May 23, 2024 by jmorenobl
2 of 4 tasks
4
make install insufficient for running llama3-8B-Instruct documentation Improvements or additions to documentation
#484 opened May 22, 2024 by fozziethebeat
2 of 4 tasks
@magdyksaleh
4
When caching adapters, cache the adapter ID + the API token pair enhancement New feature or request good first issue Good for newcomers
#479 opened May 20, 2024 by noyoshi
4
ProTip! no:milestone will show everything without a milestone.