Instructions to use leafyseay/RIME-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use leafyseay/RIME-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="leafyseay/RIME-2B")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("leafyseay/RIME-2B") model = AutoModelForMultimodalLM.from_pretrained("leafyseay/RIME-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add pipeline tag, library name, and link to paper
#1
by nielsr HF Staff - opened
This PR improves the model card for RIME-2B by:
- Adding the
pipeline_tag: feature-extractionmetadata to make the model discoverable for embedding/feature-extraction tasks. - Adding
library_name: transformersas the model uses the Qwen2-VL architecture which is natively supported by Hugging Face Transformers. - Adding a link to the corresponding paper on Hugging Face: Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings.
leafyseay changed pull request status to merged