Text Classification
Transformers
Safetensors
gemma4_unified
image-text-to-text
multimodal
merged
decision-model
Instructions to use akhilaaa3/Jev-Omni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use akhilaaa3/Jev-Omni with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="akhilaaa3/Jev-Omni")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("akhilaaa3/Jev-Omni") model = AutoModelForMultimodalLM.from_pretrained("akhilaaa3/Jev-Omni", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Make the unified bf16 checkpoint the repo root
Verified signatureServer-side copy of unified/model.safetensors to the root, with its config, generation, processor and verification files. The repo root is now one standard Transformers checkpoint, so from_pretrained works on it directly and Hugging Face can count downloads through the root config.json. jev_omni.load_jev_omni now loads this root checkpoint plus head.pt, as the Space does, instead of the fp32 backbone and a separate base-model download.6028e1f