Instructions to use wsashawn/llava_7b_lora_ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use wsashawn/llava_7b_lora_ft with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("liuhaotian/llava-v1.5-7b") model = PeftModel.from_pretrained(base_model, "wsashawn/llava_7b_lora_ft") - Notebooks
- Google Colab
- Kaggle
Download non_lora_trainables.bin from wsashawn/llava_7b_lora_ft: direct link, hf CLI and curl.
- Browser
- Download file 42 MB
-
https://huggingface.co/wsashawn/llava_7b_lora_ft/resolve/main/non_lora_trainables.bin
- Command line
-
hf download hf://wsashawn/llava_7b_lora_ft/non_lora_trainables.bin
-
curl -L -o non_lora_trainables.bin https://huggingface.co/wsashawn/llava_7b_lora_ft/resolve/main/non_lora_trainables.bin
42 MB
- Xet hash:
- 1337873472002b8f4d409879e2faaa68adfd3e4277b41562b6aa1da9d7ac1b56
- Size of remote file:
- 42 MB
- SHA256:
- 4256d30527b68662b35b87c465a72acf392ee1cb4c248edee2238d360ce1f04e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.