Instructions to use ayushk4/smol-gpt4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ayushk4/smol-gpt4 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="ayushk4/smol-gpt4")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ayushk4/smol-gpt4") model = AutoModelForMultimodalLM.from_pretrained("ayushk4/smol-gpt4", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download vision-model.bin from ayushk4/smol-gpt4: direct link, hf CLI and curl.
- Browser
- Download file 1.97 GB
-
https://huggingface.co/ayushk4/smol-gpt4/resolve/main/vision-model.bin
- Command line
-
hf download hf://ayushk4/smol-gpt4/vision-model.bin
-
curl -L -o vision-model.bin https://huggingface.co/ayushk4/smol-gpt4/resolve/main/vision-model.bin
1.97 GB
- Xet hash:
- c402adb92678c893e24e607c2d019bc75a6ff6df14e7b4203f1799fa02a8e854
- Size of remote file:
- 1.97 GB
- SHA256:
- 5133b836171fb526c0e9d6d283d7754c26864381013d5d0b286e719b6bf0ee01
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.