-
Hi,
Has anyone tried the new version of Vicuna weights? Does it work?
Thanks.
tuyra updated
11 months ago
-
# Welcome to JunYoung's blog | (LLama2) GPU에서 돌아가는 나만의 디스코드 챗봇 만들기
Discord bot, Chatting bot
[https://junia3.github.io/blog/chatbotgpu](https://junia3.github.io/blog/chatbotgpu)
-
잠깐 LLAMA3 8B모델을 써보고 있는데
솔직히 말도 안되는 성능이라서 이걸 어떻게 잘 활용할 수 있다면 엄청날 것 같아서요.
가능한지 궁금해서 적어봅니다.
nhn모델이 aihub에 있는 번역자료로 파인튜닝 됬던데
비용이 비싸지 않다면(? 그럴리가 없겠지만)
한번 파인튜닝해서 모델 만들어서 써보고 싶어서 문의를 남깁니다.
LL…
-
### Describe the feature
看到[Colossal-LLaMA-2-7B](https://github.com/hpcaitech/ColossalAI/tree/main/applications/Colossal-LLaMA-2#colossal-llama-2-7b) 实现了基于llama2的continual training
不知道是否可以基于codell…
bohea updated
9 months ago
-
-
llama2-7b-chat-hf,按照提供的量化步骤,得到4bit版本的模型并补齐模型文件,通过AutoModelForCausalLM.from_pretrained方式加载时,报NotImplementedError: Cannot copy out of meta tensor; no data!
环境配置:
accelerate==0.21.0
bitsandbytes==0.40…
-
Hi,
If I get it correctly, you have used code from https://github.com/allenai/open-instruct as base.
Would you release the full code of reproducing llama2 pro 8B?
Thanks!
-
Llama code now runs on Codon. (with a 74 X improvement compared to Python).
https://github.com/dmahurin/llama2.codon/
https://github.com/tairov/llama2.py/pull/5
But, to get this to work chang…
-
The system prompt in the [llama2 blog post](https://huggingface.co/blog/llama2) contains an extra space and new line when compared to the [original](https://github.com/facebookresearch/llama/blob/6c7f…
-
### System Info
- GPU : A5000
- CPU : x86_64
### Who can help?
@byshiue please help
### Information
- [X] The official example scripts
- [ ] My own modified scripts
### Tasks
- …