Instructions to use WGNW/tmp_chat_peft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use WGNW/tmp_chat_peft with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("WGNW/Llama-2-ko-7b-Chat-auto-gptq-4bit") model = PeftModel.from_pretrained(base_model, "WGNW/tmp_chat_peft") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 32031fb0b5775c27ac6b829052aa121c6849d0af4b90337e72cda5ebdce15e68
- Size of remote file:
- 33.6 MB
- SHA256:
- 33f1efbcd6fe30737fe77ef30f388acc820c6e3a51fc7402974aab651a0c7f04
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.