Active filters: 01choco
01choco/LLaMA-UltraFeedback-SFT-3
01choco/LLaMA-UltraFeedback-SFT-5
01choco/LLaMA-UltraFeedback-SFT-10
01choco/LLaMA-UltraFeedback-SFT-10-Full
01choco/LLaMA-UltraFeedback-SFT-3-Full
01choco/LLaMA-UltraFeedback-SFT-5-Full
01choco/LLaMA-UltraFeedback-DPO-3
8B • Updated 13B • Updated 7B • Updated 7B • Updated 7B • Updated 01choco/highavg-fine-dpo3
7B • Updated 01choco/llama2-highvar-dpo3
7B • Updated 01choco/highavg-fine-dpo2
7B • Updated 01choco/highavg-fine-dpo1
7B • Updated 01choco/llama2-highvar-dpo2
7B • Updated 01choco/llama2-highvar-dpo1
7B • Updated 7B • Updated 7B • Updated 7B • Updated 01choco/llama2-sft-highvar-dpo1
7B • Updated 01choco/llama2-sft-highvar-dpo2
7B • Updated 01choco/llama2-sft-lowavg-dpo1
7B • Updated 01choco/llama2-sft-lowavg-dpo2
7B • Updated 01choco/llama2-sft-lowavg-dpo3
7B • Updated 01choco/llama2-sft-highavg-dpo1
7B • Updated 01choco/llama2-sft-highavg-dpo2
Updated
01choco/llama2-sft-highavg-dpo3
Updated
01choco/llama2-sft-highvar-dpo3
7B • Updated 01choco/llama2-nooverlap-highavg-dpo3
7B • Updated