CriteriaPO/qwen2.5-3b-dpo-ablation-finegrained-all-vanilla-400k
Updated
CriteriaPO/qwen2.5-3b-dpo-ablation-finegrained-500k-vanilla-100k
Text Generation
• 3B • Updated
• 9
CriteriaPO/qwen2.5-3b-dpo-ablation-finegrained-200k
Text Generation
• 3B • Updated
• 18
CriteriaPO/qwen2.5-3b-dpo-vanilla-in-finegrained
Text Generation
• 3B • Updated
• 1
CriteriaPO/qwen2.5-3b-orpo-coarse-2e
CriteriaPO/qwen2.5-3b-orpo-mini-2e
Text Generation
• 3B • Updated
• 2
CriteriaPO/qwen2.5-3b-dpo-coarse-40-vanilla
Text Generation
• 3B • Updated
• 1
CriteriaPO/qwen2.5-3b-dpo-finegrained-5-vanilla
Text Generation
• 3B • Updated
• 4
CriteriaPO/qwen2.5-3b-dpo-finegrained-40-vanilla
Text Generation
• 3B • Updated
• 2
CriteriaPO/qwen2.5-3b-dpo-finegrained-20-vanilla
Text Generation
• 3B • Updated
• 2
CriteriaPO/qwen2.5-3b-dpo-finegrained-10-vanilla
Text Generation
• 3B • Updated
• 2
CriteriaPO/qwen2.5-3b-dpo-coarse-20-vanilla
Text Generation
• 3B • Updated
• 1
CriteriaPO/qwen2.5-3b-dpo-coarse-10-vanilla
Text Generation
• 3B • Updated
• 1
CriteriaPO/qwen2.5-3b-dpo-coarse-5-vanilla
Text Generation
• 3B • Updated
• 1
CriteriaPO/qwen2.5-3b-dpo-mini-40-vanilla
Text Generation
• 3B • Updated
• 1
CriteriaPO/qwen2.5-3b-dpo-mini-20-vanilla
Text Generation
• 3B • Updated
• 1
CriteriaPO/qwen2.5-3b-dpo-mini-5-vanilla
Text Generation
• 3B • Updated
• 5
CriteriaPO/qwen2.5-3b-dpo-mini-10-vanilla
Text Generation
• 3B • Updated
CriteriaPO/qwen2.5-3b-dpo-finegrained
Text Generation
• 3B • Updated
• 71
CriteriaPO/qwen2.5-3b-dpo-coarse
Text Generation
• 3B • Updated
• 57
CriteriaPO/qwen2.5-3b-dpo-mini
Text Generation
• 3B • Updated
• 54
CriteriaPO/qwen2.5-3b-dpo-vanilla
Text Generation
• 3B • Updated
• 108
CriteriaPO/llama3.2-3b-dpo-coarse
Text Generation
• 3B • Updated
• 38
CriteriaPO/llama3.2-3b-dpo-finegrained
Text Generation
• 3B • Updated
• 33
CriteriaPO/llama3.2-3b-dpo-vanilla
Text Generation
• 3B • Updated
• 82
CriteriaPO/llama3.2-3b-dpo-mini
Text Generation
• 3B • Updated
• 33
CriteriaPO/qwen2.5-3b-sft-10
Text Generation
• 3B • Updated
• 152
CriteriaPO/llama3.2-3b-sft-10
Text Generation
• 3B • Updated
• 76