Image-to-Text
Transformers
Safetensors
qwen2_5_vl
image-text-to-text
Eval Results
text-generation-inference
Instructions to use TainU/RePlan-Qwen2.5-VL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TainU/RePlan-Qwen2.5-VL-7B 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="TainU/RePlan-Qwen2.5-VL-7B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("TainU/RePlan-Qwen2.5-VL-7B") model = AutoModelForMultimodalLM.from_pretrained("TainU/RePlan-Qwen2.5-VL-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Improve model card: Add metadata, fix paper link, and add GitHub badge
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card by:
- Adding the
pipeline_tag: image-to-imagefor better categorization and discoverability. - Specifying
library_name: transformersto enable the automated "Use in Transformers" widget, as evidenced by thetransformersimports in the usage example. - Adding the
license: apache-2.0to clearly state the model's licensing. - Fixing the broken arXiv paper link in the badges and adding a new badge for the Hugging Face paper page.
- Adding a new badge for the GitHub repository, making it easier for users to find the code.
- Including an explicit link to the paper right after the main title.
- Removing the extraneous "File information" section at the end.
These updates aim to improve the model card's completeness, searchability, and usability.
TainU changed pull request status to merged