Instructions to use srivassid/drishti with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use srivassid/drishti with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-12B-it") model = PeftModel.from_pretrained(base_model, "srivassid/drishti") - Notebooks
- Google Colab
- Kaggle
Download code/prompts.py from srivassid/drishti: direct link, hf CLI and curl.
- Browser
- Download file 949 Bytes
-
https://huggingface.co/srivassid/drishti/resolve/main/code/prompts.py
- Command line
-
hf download hf://srivassid/drishti/code/prompts.py
-
curl -L -o prompts.py https://huggingface.co/srivassid/drishti/resolve/main/code/prompts.py
949 Bytes
| """Instruction variants. Picked deterministically per sample id (see schema.pick).""" | |
| CAPTION = [ | |
| "Describe this image in detail.", | |
| "Write a caption for this image.", | |
| "What is shown in this image? Describe it.", | |
| "Give a short description of this image.", | |
| ] | |
| ARTICLE = [ | |
| "Write the article that goes with these images.", | |
| "Write the text of the web page these images come from.", | |
| ] | |
| OCR_PAGE = [ | |
| "Read all the text in this image.", | |
| "Transcribe all the text in this document page.", | |
| "Extract the text from this image exactly as written.", | |
| "What does the text in this image say? Write it out in full.", | |
| ] | |
| OCR_CROP = [ | |
| "Read the text in this image.", | |
| "What does the text say?", | |
| "Transcribe the text in this image.", | |
| ] | |
| SCENE_TEXT_BOXES = [ | |
| "Detect and read all the text in this image. For each piece of text give the text and its " | |
| "bounding box as [x1, y1, x2, y2], normalized to 0-999.", | |
| ] | |