Instructions to use hkondle/CapstoneMainModel-10ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hkondle/CapstoneMainModel-10ep with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-text", model="hkondle/CapstoneMainModel-10ep")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("hkondle/CapstoneMainModel-10ep") model = AutoModelForMultimodalLM.from_pretrained("hkondle/CapstoneMainModel-10ep", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from hkondle/CapstoneMainModel-10ep: direct link, hf CLI and curl.
- Browser
- Download file 224 Bytes
-
https://huggingface.co/hkondle/CapstoneMainModel-10ep/resolve/main/README.md
- Command line
-
hf download hf://hkondle/CapstoneMainModel-10ep/README.md
-
curl -L -o README.md https://huggingface.co/hkondle/CapstoneMainModel-10ep/resolve/main/README.md
224 Bytes
metadata
license: mit
library_name: transformers
pipeline_tag: image-to-text
base_model: Salesforce/blip-image-captioning-base
tags:
- blip
- accessibility
- diagram-captioning
VisAble diagram captioner
VisAble 10 epochs