Instructions to use HeshamHaroon/llama-2-7b-chat-ar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HeshamHaroon/llama-2-7b-chat-ar with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NousResearch/Llama-2-7b-chat-hf") model = PeftModel.from_pretrained(base_model, "HeshamHaroon/llama-2-7b-chat-ar") - Notebooks
- Google Colab
- Kaggle
Rename config.json back to adapter_config.json
#2
by isrouush - opened
Hi, I'm currently trying to use your model (life saving by the way, thank you so much!) but it's raising an error : ValueError: Can't find 'adapter_config.json' at 'HeshamHaroon/llama-2-7b-chat-ar'
I'm guessing it's because you renamed the old adapter_config.json file to config.json
is it possible to upload a copy of this file under the original name please? thank youu!
updated, you can check it .
updated, you can check it .
Thank you! but I think you've mistakenly named the file adapter_config.json.json instead of adapter_config.json haha
done , :D
thank you so much! :)
isrouush changed pull request status to closed