Instructions to use smart-assistant/falcon-7b-multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use smart-assistant/falcon-7b-multi with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-7b-instruct") model = PeftModel.from_pretrained(base_model, "smart-assistant/falcon-7b-multi") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from smart-assistant/falcon-7b-multi: direct link, hf CLI and curl.
- Browser
- Download file 9.46 MB
-
https://huggingface.co/smart-assistant/falcon-7b-multi/resolve/main/adapter_model.bin
- Command line
-
hf download hf://smart-assistant/falcon-7b-multi/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/smart-assistant/falcon-7b-multi/resolve/main/adapter_model.bin
9.46 MB
- Xet hash:
- 54ebdd1e9c80a153cfc2bea01dc369ee30affdfe29ff7c263b7e887a340da9a4
- Size of remote file:
- 9.46 MB
- SHA256:
- 9caded510e995fcf9928440c946e628918d5c584cc7a22fefe0aa71679def4b6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.