Any-to-Any
Transformers
Safetensors
English
Chinese
qwen2_5_vl
text-generation
text-generation-inference
Instructions to use PaDT-MLLM/PaDT_REC_7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PaDT-MLLM/PaDT_REC_7B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("PaDT-MLLM/PaDT_REC_7B") model = AutoModelForSeq2SeqLM.from_pretrained("PaDT-MLLM/PaDT_REC_7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Improve model card: Add `transformers` library and refine pipeline tags
#1
by nielsr HF Staff - opened
This PR enhances the model card for Patch-as-Decodable Token (PaDT) by:
- Adding
library_name: transformers, which enables direct integration and automated code snippets via the Hugging Facetransformerslibrary, as evidenced by the sample usage. - Refining the
pipeline_taginto a listpipeline_tagsincluding bothimage-text-to-textandimage-segmentation. This accurately reflects the model's capabilities to generate both textual and diverse visual outputs, including segmentation masks, as described in the paper abstract and showcase examples. - Updating the introductory sentence for the sample usage section to match the GitHub README for better context.
These changes will improve the model's discoverability on the Hub and provide clearer guidance for users.
PaDT-MLLM changed pull request status to closed