prithivMLmods

/

Open-R1-Mini-Experimental

like 10

From my progress, it performed well in math explanations, quiz explanations, and diagram-based conditional answering. However, I think it lacked some general-purpose evidence in training. Lemme analyze it!

Yes, I have noticed it. I'll let you know once it is fixed. If possible, could you share the inference here if it’s not a bother? Did you try it with Quants?

checkout: https://huggingface.co/prithivMLmods/Open-R1-Mini-Experimental/blob/main/open-r1-reasoner-doc-py/openr1.ipynb

Example	Image
Example 1
Example 2
Example 3
Example 4
Example 5