Curated SFT datasets for instruction-following and conversational fine-tuning
Behrooz Azarkhalili
ermiaazarkhalili
AI & ML interests
LLMs, VLMs, PEFT, RL for LLMs and VLMs.
Organizations
models 43
ermiaazarkhalili/LFM2-700M-GRPO-NuminaMath-50K
Updated
ermiaazarkhalili/LFM2-350M-GRPO-NuminaMath-50K
Updated
ermiaazarkhalili/SmolLM2-135M-Instruct-GRPO-NuminaMath-50K
Updated
ermiaazarkhalili/SmolLM2-1.7B-Instruct-GRPO-NuminaMath-50K
Updated
ermiaazarkhalili/LFM2-2.6B-GRPO-NuminaMath-50K
Updated
ermiaazarkhalili/Qwen3-0.6B-GRPO-NuminaMath-100K
Updated
ermiaazarkhalili/Qwen2.5-0.5B-Instruct-GRPO-NuminaMath-100K
Updated
ermiaazarkhalili/Qwen3-0.6B-GRPO-NuminaMath-50K
Updated
ermiaazarkhalili/Qwen2.5-0.5B-Instruct-GRPO-NuminaMath-50K
Updated
ermiaazarkhalili/Qwen2.5-0.5B-SFT-OpenHermes-2.5-100-GGUF
0.5B • Updated
• 11
datasets 6
ermiaazarkhalili/alpaca-gpt4-short-100tok
Viewer
• Updated
• 5k • 8
ermiaazarkhalili/orca-mini-short-100tok
Viewer
• Updated
• 5k • 8
ermiaazarkhalili/orca-mini-v1-high-prob-qwen-0.5b-10k
Viewer
• Updated
• 10k • 14
ermiaazarkhalili/alpaca-gpt4-en-high-prob-qwen-0.5b-10k
Viewer
• Updated
• 10k • 14
ermiaazarkhalili/alpaca-cleaned-high-prob-qwen-0.5b-10k
Viewer
• Updated
• 10k • 16
ermiaazarkhalili/alpaca-high-prob-qwen-0.5b-10k
Viewer
• Updated
• 10k • 17