Pouria Mahdavinia's picture

1 1

Pouria Mahdavinia PRO

pmahdavi

·

AI & ML interests

Model Merging, Distributed Training, and Memory-Efficient Training

Recent Activity

updated a model 2 days ago

pmahdavi/Olmo-3-7B-Think-Math-Code

published a model 2 days ago

pmahdavi/Olmo-3-7B-Think-Math-Code

updated a model 4 days ago

pmahdavi/Olmo-3-7B-RL-Zero-Math-Code

View all activity

Organizations

Papers 1

arxiv:2509.11167

spaces 1

FFG Mask Explorer

Generate masks for language models to visualize pruning

models 8

pmahdavi/Olmo-3-7B-Think-Math-Code

Text Generation • 7B • Updated 2 days ago • 51 • 1

pmahdavi/Olmo-3-7B-RL-Zero-Math-Code

Text Generation • 7B • Updated 4 days ago • 412 • 1

pmahdavi/Llama-3.1-8B-coding-tulu3-ebs128-lr5e6-wsdcr0p4

Text Generation • 8B • Updated Sep 29, 2025 • 4

pmahdavi/Llama-3.1-8B-general

Text Generation • 8B • Updated Sep 29, 2025 • 16

pmahdavi/Llama-3.1-8B-coding

Text Generation • 8B • Updated Sep 29, 2025 • 9

pmahdavi/Llama-3.1-8B-knowledge-recall

Text Generation • 8B • Updated Sep 29, 2025 • 13

pmahdavi/Llama-3.1-8B-precise-if

Text Generation • 8B • Updated Sep 29, 2025 • 7

pmahdavi/Llama-3.1-8B-math-reasoning

Text Generation • 8B • Updated Sep 29, 2025 • 9

datasets 9

pmahdavi/proof-verifier-qwen3-8b

Viewer • Updated Dec 7, 2025 • 80 • 11

pmahdavi/dolci-math_olmo3-32b_gemini-2.5-flash

Viewer • Updated Dec 5, 2025 • 512 • 12

pmahdavi/dolci-math_olmo3-32b_gemini-2.5-flash-lite

Viewer • Updated Dec 5, 2025 • 512 • 7

pmahdavi/olmo3-math-flash2.5

Viewer • Updated Dec 4, 2025 • 512 • 7

pmahdavi/olmo3-math-128-j2

Viewer • Updated Dec 4, 2025 • 512 • 9

pmahdavi/olmo3-math-128

Viewer • Updated Dec 4, 2025 • 512 • 5

pmahdavi/olmo3-math-test

Viewer • Updated Dec 3, 2025 • 20 • 7

pmahdavi/acereason-synthetic-data

Viewer • Updated Dec 2, 2025 • 800 • 4

pmahdavi/gsm8k-sft-test

Viewer • Updated Nov 26, 2025 • 10 • 4