esfrankel17/dpo-UF-Qwen2.5-7B-type1-bs32-lr5e-7-ep1-gold1.0-lbda0.0-ps-Qwen2.5-0.5B-beta2
8B • Updated
• 1
Eric Frankel
esfrankel17
AI & ML interests
None yet
Organizations
esfrankel17/dpo-UF-Qwen2.5-7B-type1-bs32-lr5e-7-ep1-gold1.0-lbda0.0-ps-Qwen2.5-0.5B-beta0.1
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type1-bs32-lr5e-7-ep1-gold1.0-lbda0.0-ps-Qwen2.5-0.5B-beta5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type1-bs32-lr5e-7-ep1-gold1.0-lbda0.0-ps-Qwen2.5-0.5B-beta2
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type1-bs32-lr5e-7-ep1-gold1.0-lbda0.0-ps-Qwen2.5-0.5B-beta1
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type1-bs32-lr5e-7-ep1-gold1.0-lbda0.0-ps-Qwen2.5-0.5B-beta0.5
8B • Updated
• 1
esfrankel17/dpo-HS2-Qwen2.5-7B-type1-bs32-lr5e-7-ep1-gold1.0-lbda0.0-ps-Qwen2.5-0.5B-beta0.1
8B • Updated
• 1
esfrankel17/rm-UF2HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep1-gold1.0-lbda0.5-ps-Qwen2.5-72B
7B • Updated
• 1
esfrankel17/rm-UF2HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep2-gold0.7-lbda0.7-ps-Qwen2.5-7B
7B • Updated
• 1
esfrankel17/rm-UF2HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep2-gold0.7-lbda0.6-ps-Qwen2.5-7B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep2-gold0.7-lbda0.4-ps-Qwen2.5-7B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep1-gold0.5-lbda0.9-ps-Qwen2.5-7B
Updated
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep2-gold0.7-lbda0.1-ps-Qwen2.5-72B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep2-gold0.9-lbda0.0-ps-Qwen2.5-0.5B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep2-gold0.5-lbda0.4-ps-Qwen2.5-0.5B
Updated
esfrankel17/rm-UF2HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep2-gold0.01-lbda0.2-ps-Qwen2.5-72B
Updated
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep2-gold0.01-lbda0.8-ps-Qwen2.5-72B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep2-gold0.1-lbda0.6-ps-Qwen2.5-0.5B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep1-gold0.1-lbda0.7-ps-Qwen2.5-0.5B
7B • Updated
• 1
esfrankel17/rm-UF2HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep2-gold0.01-lbda0.3-ps-Qwen2.5-0.5B
Updated
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep1-gold0.3-lbda0.2-ps-Qwen2.5-72B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep1-gold0.1-lbda0.9-ps-Qwen2.5-72B
Updated
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep1-gold0.3-lbda0.0-ps-Qwen2.5-7B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep1-gold0.1-lbda0.8-ps-Qwen2.5-0.5B
7B • Updated
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep1-gold0.1-lbda0.8-ps-Qwen2.5-7B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep1-gold0.3-lbda0.0-ps-Qwen2.5-72B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep2-gold0.3-lbda0.1-ps-Qwen2.5-0.5B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep2-gold0.01-lbda0.5-ps-Qwen2.5-7B
7B • Updated
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-05-ep2-gold0.01-lbda0.9-ps-Qwen2.5-0.5B
7B • Updated
• 1
esfrankel17/rm-HS2-Qwen2.5-7B-type4-bs128-lr1e-06-ep1-gold0.1-lbda0.6-ps-Qwen2.5-7B
7B • Updated
• 1