Instructions to use SwatiM/opt-6.7b-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SwatiM/opt-6.7b-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("facebook/opt-6.7b") model = PeftModel.from_pretrained(base_model, "SwatiM/opt-6.7b-lora") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from SwatiM/opt-6.7b-lora: direct link, hf CLI and curl.
- Browser
- Download file 33.6 MB
-
https://huggingface.co/SwatiM/opt-6.7b-lora/resolve/main/adapter_model.bin
- Command line
-
hf download hf://SwatiM/opt-6.7b-lora/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/SwatiM/opt-6.7b-lora/resolve/main/adapter_model.bin
33.6 MB
- Xet hash:
- f2f3290850e77f5bde3029e099b02e80ff75a3f99259efc921b2cb6716286e75
- Size of remote file:
- 33.6 MB
- SHA256:
- a657c16afb6e5517da3c3e6d074e48ffa83f41e9b0f3511a514d18a8a422b90c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.