Image-Text-to-Text
PEFT
Safetensors
English
lora
qlora
4-bit precision
adapter
medical
radiology
image-captioning
image-to-text
llava-onevision
qwen2
vision-language
imageclef
rocov2
conversational
Instructions to use HoqueMahmudul/llava-onevision-7b-qlora-radiology-image-caption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HoqueMahmudul/llava-onevision-7b-qlora-radiology-image-caption with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("llava-hf/llava-onevision-qwen2-7b-ov-hf") model = PeftModel.from_pretrained(base_model, "HoqueMahmudul/llava-onevision-7b-qlora-radiology-image-caption") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.safetensors from HoqueMahmudul/llava-onevision-7b-qlora-radiology-image-caption: direct link, hf CLI and curl.
- Browser
- Download file 161 MB
-
https://huggingface.co/HoqueMahmudul/llava-onevision-7b-qlora-radiology-image-caption/resolve/main/adapter_model.safetensors
- Command line
-
hf download hf://HoqueMahmudul/llava-onevision-7b-qlora-radiology-image-caption/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/HoqueMahmudul/llava-onevision-7b-qlora-radiology-image-caption/resolve/main/adapter_model.safetensors
161 MB
- Xet hash:
- 101e8da38114edd830b02f5f5dc0eb5d5aa8d37c793973cd23431197c646c512
- Size of remote file:
- 161 MB
- SHA256:
- 9e9f9bbda111b30e52eadb9772582f20faf53b076773fe570c1860b0668e08ef
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.