Instructions to use opencompass/CompassJudger-2-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use opencompass/CompassJudger-2-7B-Instruct with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("opencompass/CompassJudger-2-7B-Instruct") model = AutoModelForCausalLM.from_pretrained("opencompass/CompassJudger-2-7B-Instruct") - Notebooks
- Google Colab
- Kaggle
Improve model card: Add pipeline tag, library name, and relevant tags; update paper link in content
#2
by nielsr HF Staff - opened
This PR improves the model card by:
- Adding the
pipeline_tag: text-generationto ensure the model appears in relevant searches on the Hugging Face Hub. - Adding
library_name: transformersto enable the "Use in Transformers" widget for direct copy-pasting code snippets. - Adding
llm-as-judgeandqwen2to thetagslist for enhanced discoverability. - Updating the paper link in the "Evaluation" section to point to the Hugging Face paper page (
https://huggingface.co/papers/2507.09104) for better integration with the Hugging Face ecosystem.
iridescentttt changed pull request status to merged