Image-to-Text
Transformers
Safetensors
English
qwen3_vl
image-text-to-text
uni-mumer
hmer
math-ocr
handwritten-math
latex
qwen3-vl
vision-language
Instructions to use phxember/Uni-MuMER-Qwen3-VL-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use phxember/Uni-MuMER-Qwen3-VL-2B 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="phxember/Uni-MuMER-Qwen3-VL-2B")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("phxember/Uni-MuMER-Qwen3-VL-2B") model = AutoModelForMultimodalLM.from_pretrained("phxember/Uni-MuMER-Qwen3-VL-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- dde3c5a4d468da6fe61f11ffa8f04af2d101f8f4a0fe118c37bd31bb8c3017b6
- Size of remote file:
- 11.4 MB
- SHA256:
- be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.