Comments (5)
Hello!
I noticed that you're working with the KoAlpaca-65B-LoRA repository at huggingface, which contains only the 'LoRA-finetuned' additional weights.
To load the original llama weights, you can use other codes, such as the alpaca-lora found here: https://github.com/tloen/alpaca-lora.
If you're looking to load the model and test it on your own device, please note that you'll need an A100 80G GPU or H100 GPU to load it in a single device, even when using 8-bit quantization.
I won't be discussing pipeline parallel or tensor parallel in this repository, as it isn't the right place for that.
Assuming you have the necessary GPU, you can follow these steps to load the model and try it out: https://github.com/deep-diver/Alpaca-LoRA-Serve
To install alpaca-lora-serve, just follow the instructions in the repository.
Once that's done, you can run the following command:
export BASE_URL=decapoda-research/llama-65b-hf
export FINETUNED_CKPT_URL=beomi/KoAlpaca-65B-LoRA
python app.py --base_url $BASE_URL --ft_ckpt_url $FINETUNED_CKPT_URL --port 6006
After that, you can access the chatbot-like web UI from your browser at http://localhost:6006. Enjoy and happy coding!
from koalpaca.
from koalpaca.
I just did whatever you mentioned, but I got this error:
unsupported model type. only llamastack, alpaca, flan, and baize are supported
did I miss something?
(Alpaca-LoRA as a Chatbot Service works well)
from koalpaca.
I utilized the alpaca-lora framework for training the LoRA model; however, I did not employ it for loading or using the model.
My experience with the LoRA checkpoint has been limited to its integration within the Chatbot service.
What are you trying to do exactly?
from koalpaca.
based on your guidance, I just install alpaca-lora-serve
then run the exact same command that you shared to check it on my machine
but I got that error
for now I just want to test it on my system, and maybe later try to use the model for the specific task :)
from koalpaca.
Related Issues (20)
- LLaMa 30B, 65B token은 7B token 그대로 써도 되는건가요?? HOT 1
- 허깅 페이스의 TGI 이미지로 KoAlpaca-Polyglot-12.8B docker 컨테이너 생성하려고 하는데 오류가 발생됩니다. HOT 1
- chat-ui description 수정 HOT 1
- PEFT로LoRA로드 중에 에러
- decapoda-research/llama-13b-hf 모델이 사라졌습니다. HOT 1
- 학습한 LLM 모델이 말을 끝내지 않고 계속 생성합니다. HOT 5
- KoAlpaca polyglot 12.8b Fine-tuning 시 에러문의 드립니다. HOT 2
- KoAlpaca 모델 실행 예시코드 실행 중 용량 초과로 취소된 문제에 대해 문의드려요.
- ko-alpaca 1.0 데이터셋 관련 문의 HOT 1
- Few-shot 평가 문의
- index.json 파일 문의 드립니다 HOT 1
- beomi/KoAlpaca-Polyglot-12.8B 로 inference를 진행하기 위해서는 48GB의 VRAM이 필요한가요? HOT 3
- prompt 관련 ko_alpaca_data.json 형식 문의 드립니다. HOT 1
- 학습 결과 inference시 질문좀 드리겠습니다.! HOT 3
- 모델 저장 및 허깅페이스에 올리는법..이것때문에 문제가 생기네요 ㅠㅠ HOT 1
- 원하는 형태의 답변으로 고정시킬 수 있는 방법이 있을까요? HOT 4
- NSMC 결과 reproducing HOT 1
- 상업적 이용 가능 여부 관련 HOT 2
- 데모에 성능에 대해 질문있습니다. HOT 1
- Citation 관련 문의드립니다
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from koalpaca.