Instructions to use yuta24/ui-test-vision-2b-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use yuta24/ui-test-vision-2b-alpha with PEFT:
Task type is invalid.
- MLX
How to use yuta24/ui-test-vision-2b-alpha with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("yuta24/ui-test-vision-2b-alpha") config = load_config("yuta24/ui-test-vision-2b-alpha") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
File size: 601 Bytes
e379257 | 1 2 3 4 5 6 7 8 9 10 11 | # NOTICE
`glint/joint_schema_model.py` is copied unmodified (except for a 3-line header comment)
from Cloudflare's Clef-Flash release: https://huggingface.co/Cloudflare/clef-flash
It is licensed under the Apache License, Version 2.0 (see `LICENSE-CLEF-APACHE-2.0.txt`).
Glint uses `JointSchemaHead`, `ClefModel`, `encode_record` and `collate_records` from it, with a
freshly initialised head sized for the student backbone (no Clef weights are included in this repo).
The student backbone (Qwen/Qwen3.5-2B, Qwen/Qwen3.5-0.8B) is Apache-2.0 and is downloaded from Hugging Face at runtime.
|