·
AI & ML interests
None yet
Organizations
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.9-lbda0.4-ps-Qwen2.5-7B-beta0.5
8B • Updated
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.5-lbda0.4-ps-Qwen2.5-7B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold1.0-lbda0.4-ps-Qwen2.5-72B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.7-lbda0.4-ps-Qwen2.5-72B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold1.0-lbda0.4-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.1-lbda0.4-ps-Qwen2.5-72B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.1-lbda0.4-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.5-lbda0.4-ps-Qwen2.5-72B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.7-lbda0.4-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.01-lbda0.4-ps-Qwen2.5-7B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.3-lbda0.4-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.9-lbda0.2-ps-Qwen2.5-72B-beta0.5
8B • Updated
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.01-lbda0.6-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.9-lbda0.2-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.5-lbda0.2-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.3-lbda0.2-ps-Qwen2.5-7B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.3-lbda0.2-ps-Qwen2.5-72B-beta0.5
8B • Updated
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.7-lbda0.2-ps-Qwen2.5-7B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.1-lbda0.2-ps-Qwen2.5-7B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.01-lbda0.2-ps-Qwen2.5-72B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.9-lbda0.2-ps-Qwen2.5-7B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold1.0-lbda0.2-ps-Qwen2.5-7B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.5-lbda0.2-ps-Qwen2.5-7B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold1.0-lbda0.2-ps-Qwen2.5-72B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.7-lbda0.2-ps-Qwen2.5-72B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold1.0-lbda0.2-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.1-lbda0.2-ps-Qwen2.5-72B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.1-lbda0.2-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.5-lbda0.2-ps-Qwen2.5-72B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type4-bs32-lr5e-7-ep1-gold0.7-lbda0.2-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1