Active filters: obiwit
obiwit/llama3.2-3b-sft-full
Text Generation
• 3B • Updated • 29
obiwit/llama3.2-3b-dpo-mini
Text Generation
• 3B • Updated • 11
obiwit/llama3.2-3b-dpo-vanilla
Text Generation
• 3B • Updated • 32
obiwit/llama3.2-3b-dpo-coarse
3B • Updated • 11
obiwit/llama3.2-3b-dpo-finegrained
3B • Updated • 13
obiwit/llama3.2-3b-dpo-mini-vanilla
3B • Updated • 12
obiwit/llama3.2-3b-dpo-vanilla-subset
Text Generation
• 3B • Updated • 15
obiwit/backup-llama3.2-3b-dpo-mr
Text Generation
• 3B • Updated • 20
obiwit/llama3.2-3b-dpo-mini-reasoning
Text Generation
• 3B • Updated • 11
obiwit/qwen2.5-3b-sft-full
Text Generation
• 3B • Updated • 19
obiwit/gemma-3-4b-sft-full
Text Generation
• 4B • Updated • 32
obiwit/qwen2.5-3b-dpo-mini
Text Generation
• 3B • Updated • 2
obiwit/qwen2.5-3b-dpo-vanilla
Updated
obiwit/llama3.2-3b-orpo-mini
Text Generation
• 3B • Updated • 7
obiwit/llama3.2-3b-dpo-mini-2ep
Text Generation
• 3B • Updated • 9
Text Generation
• 3B • Updated • 16
Text Generation
• 3B • Updated • 11
obiwit/llama3.2-3b-orpo-mini-OLD
Text Generation
• 3B • Updated • 8
obiwit/llama3.2-3b-orpo-vanilla-OLD
Text Generation
• 3B • Updated • 14
obiwit/llama3.2-3b-orpo-coarse-OLD
Text Generation
• 3B • Updated • 12
obiwit/llama3.2-3b-orpo-finegrained-OLD
Text Generation
• 3B • Updated • 6
obiwit/llama3.2-3b-dpo-coarse-OLD
Text Generation
• 3B • Updated • 15
obiwit/llama3.2-3b-dpo-vanilla-OLD
Text Generation
• 3B • Updated • 4
obiwit/llama3.2-3b-dpo-mini-OLD
Text Generation
• 3B • Updated • 3
obiwit/llama3.2-3b-dpo-finegrained-OLD
Text Generation
• 3B • Updated • 10
obiwit/qwen2.5-3b-orpo-vanilla
Text Generation
• 3B • Updated • 14
obiwit/qwen2.5-3b-orpo-coarse
Text Generation
• 3B • Updated • 21
obiwit/qwen2.5-3b-orpo-mini
Text Generation
• 3B • Updated • 6
obiwit/llama3.2-3b-dpo-mini-NO-DD-OLD
Text Generation
• 3B • Updated • 10
obiwit/llama3.2-3b-dpo-mini-sft-10-OLD
Text Generation
• 3B • Updated • 7