Image-Text-to-Text
PEFT
Safetensors
English
ocr_test
qwen
qvq
kie
trl
text-generation-inference
qwen2_vl
conversational
Instructions to use prithivMLmods/QvQ-KiE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use prithivMLmods/QvQ-KiE with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Qwen2-VL-OCR-2B-Instruct") model = PeftModel.from_pretrained(base_model, "prithivMLmods/QvQ-KiE") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from prithivMLmods/QvQ-KiE: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/prithivMLmods/QvQ-KiE/resolve/main/tokenizer.json
- Command line
-
hf download hf://prithivMLmods/QvQ-KiE/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/prithivMLmods/QvQ-KiE/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- f030189151b6e970ad5bcd72ad866113fb1f5de08c816b6d45131513ba67ed71
- Size of remote file:
- 11.4 MB
- SHA256:
- 91c6c9822d89e896452cf16cb37208a713fd4aa5b2af2beeb37952970c8ed0d7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.