Open Models, Ready for Production

dpo_oasst1_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43

dpo_gsm8k_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43

dpo_gsm8k_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44

dpo_gsm8k_qwen3.5-4b_as_qwen3.6-35b-a3b_seed43

dpo_oasst1_gpt-oss-20b_as_gpt-oss-120b_seed43

dpo_oasst1_qwen3.6-35b-a3b_as_gpt-oss-20b_seed42

ecomm-db-stage2-sft-merged

dpo_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed44

dpo_gsm8k_gpt-oss-120b_as_qwen3.6-27b_seed43

dpo_gsm8k_qwen3.5-4b_as_qwen3.6-27b_seed44

granite-4.1-3b

xl-24

ft_wspr_sm_jt_128_256_fold5

dpo_gsm8k_gpt-oss-20b_as_qwen3.6-35b-a3b_seed44

dpo_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43

dpo_gsm8k_gpt-oss-120b_as_qwen3.6-27b_seed44

dpo_gsm8k_qwen3.6-27b_as_qwen3.5-4b_seed44

dpo_gsm8k_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42

dpo_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44

dpo_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42

vylex-counselor-v1

dpo_gsm8k_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

dpo_oasst1_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed42

dpo_gsm8k_gpt-oss-20b_as_qwen3.6-35b-a3b_seed43

dpo_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed43

dpo_gsm8k_gpt-oss-20b_as_qwen3.6-35b-a3b_seed42

dpo_gsm8k_qwen3.6-27b_as_qwen3.5-4b_seed42

dpo_gsm8k_gpt-oss-20b_as_qwen3.6-27b_seed44

dpo_gsm8k_gpt-oss-120b_as_qwen3.6-27b_seed42

Gege24

clobber-ic-9770-mobility

dpo_gsm8k_qwen3.6-35b-a3b_as_qwen3.6-27b_seed44

dpo_gsm8k_qwen3.5-4b_as_qwen3.6-27b_seed43

dpo_gsm8k_qwen3.6-27b_as_qwen3.5-4b_seed43

dpo_gsm8k_gpt-oss-120b_as_qwen3.6-27b_seed1

dpo_gsm8k_qwen3.5-4b_as_qwen3.6-27b_seed42

dpo_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed42

dpo_gsm8k_qwen3.5-4b_as_nemotron-nano-30b-a3b_seed44

dpo_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed44

dpo_gsm8k_qwen3.6-35b-a3b_as_qwen3.6-27b_seed42

llama-3.2-3b-taiwan-chat-clean-lora

dpo_gsm8k_gpt-oss-20b_as_qwen3.6-27b_seed43

dpo_gsm8k_qwen3.5-4b_as_nemotron-nano-30b-a3b_seed43

dpo_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed43