🔄 In a Training Loop

Behrooz Azarkhalili

ermiaazarkhalili

·

AI & ML interests

LLMs, VLMs, PEFT, RL for LLMs and VLMs.

Recent Activity

updated a model about 3 hours ago

ermiaazarkhalili/SmolLM3-3B-GRPO-NuminaMath-10K-GGUF

published a model about 3 hours ago

ermiaazarkhalili/SmolLM3-3B-GRPO-NuminaMath-10K-GGUF

updated a model about 3 hours ago

ermiaazarkhalili/Llama-3.2-3B-Instruct-GRPO-NuminaMath-10K-GGUF

View all activity

Organizations

ermiaazarkhalili 's datasets 7

ermiaazarkhalili/datasets-genbank-test

Updated 1 day ago • 12

ermiaazarkhalili/alpaca-gpt4-short-100tok

Viewer • Updated Dec 20, 2025 • 5k • 31

ermiaazarkhalili/orca-mini-short-100tok

Viewer • Updated Dec 20, 2025 • 5k • 21

ermiaazarkhalili/orca-mini-v1-high-prob-qwen-0.5b-10k

Viewer • Updated Dec 16, 2025 • 10k • 8

ermiaazarkhalili/alpaca-gpt4-en-high-prob-qwen-0.5b-10k

Viewer • Updated Dec 16, 2025 • 10k • 21

ermiaazarkhalili/alpaca-cleaned-high-prob-qwen-0.5b-10k

Viewer • Updated Dec 16, 2025 • 10k • 17

ermiaazarkhalili/alpaca-high-prob-qwen-0.5b-10k

Viewer • Updated Dec 16, 2025 • 10k • 16