Curated SFT datasets for instruction-following and conversational fine-tuning
Behrooz Azarkhalili
ermiaazarkhalili
AI & ML interests
LLMs, VLMs, PEFT, RL for LLMs and VLMs.
Recent Activity
updated a model about 22 hours ago
ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Reasoning-Unsloth-GGUF published a model about 22 hours ago
ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Reasoning-Unsloth-GGUF updated a model about 22 hours ago
ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-GGUFOrganizations
models 54
ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Reasoning-Unsloth-GGUF
Text Generation • 1B • Updated • 95
ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth-GGUF
Text Generation • 0.8B • Updated • 170
ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-GGUF
Text Generation • 0.8B • Updated • 157
ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Reasoning-Unsloth
Text Generation • 1B • Updated • 492
ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning-Unsloth
Text Generation • 0.9B • Updated • 457
ermiaazarkhalili/Qwen3.5-0.8B-SFT-Claude-Reasoning
Text Generation • 0.8B • Updated • 851 • 2
ermiaazarkhalili/Qwen2.5-3B-GRPO-NuminaMath-100K-GGUF
Updated
ermiaazarkhalili/granite-4.0-micro-GRPO-NuminaMath-100K-GGUF
Updated
ermiaazarkhalili/granite-4.0-micro-GRPO-NuminaMath-100K
Updated
ermiaazarkhalili/Qwen2.5-3B-GRPO-NuminaMath-100K
Updated
datasets 6
ermiaazarkhalili/alpaca-gpt4-short-100tok
Viewer • Updated • 5k • 13
ermiaazarkhalili/orca-mini-short-100tok
Viewer • Updated • 5k • 9
ermiaazarkhalili/orca-mini-v1-high-prob-qwen-0.5b-10k
Viewer • Updated • 10k • 8
ermiaazarkhalili/alpaca-gpt4-en-high-prob-qwen-0.5b-10k
Viewer • Updated • 10k • 16
ermiaazarkhalili/alpaca-cleaned-high-prob-qwen-0.5b-10k
Viewer • Updated • 10k • 9
ermiaazarkhalili/alpaca-high-prob-qwen-0.5b-10k
Viewer • Updated • 10k • 20