Instructions to use cimol/1447fbf6-d67c-455c-9bcf-cfc8ffa8cc29 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use cimol/1447fbf6-d67c-455c-9bcf-cfc8ffa8cc29 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Intel/neural-chat-7b-v3-3") model = PeftModel.from_pretrained(base_model, "cimol/1447fbf6-d67c-455c-9bcf-cfc8ffa8cc29") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from cimol/1447fbf6-d67c-455c-9bcf-cfc8ffa8cc29: direct link, hf CLI and curl.
- Browser
- Download file 671 MB
-
https://huggingface.co/cimol/1447fbf6-d67c-455c-9bcf-cfc8ffa8cc29/resolve/main/adapter_model.bin
- Command line
-
hf download hf://cimol/1447fbf6-d67c-455c-9bcf-cfc8ffa8cc29/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/cimol/1447fbf6-d67c-455c-9bcf-cfc8ffa8cc29/resolve/main/adapter_model.bin
671 MB
- Xet hash:
- 668c116a2cf31d660c84e494c968e154a7c3bb2bca6223032a792949fa33c516
- Size of remote file:
- 671 MB
- SHA256:
- 0e9605dc21cad05a8bf031458f352d0a06038c8312ef7b8764bab3b9064aaeda
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.