Umair Abbas
umairsiddiquie
AI & ML interests
None yet
Recent Activity
updated a collection 20 days ago
Simbox published a model about 1 month ago
umairsiddiquie/statecraft reacted to alibidaran's post with ❤️ 6 months ago
This shared notebook comprises the MMLU benchmark evaluating task for my latest reasoning model for the sociology field. The results show that using Few-shot prompting in the system prompt can significantly improve the model's performance at answering questions.
Model's link:
https://huggingface.co/alibidaran/GRPO_LLAMA3-instructive_reasoning1
Notebook evaluation:
https://www.kaggle.com/code/alibidaran/mmlu-socialogy-thinking-evals?scriptVersionId=277240033Organizations
[Cache Request] google/siglip2-giant-opt-patch16-384
#572 opened 8 months ago
by umairsiddiquie