Open Models, Ready for Production

dpo_oasst1_qwen3.6-35b-a3b_as_qwen3.5-4b_seed42

dpo_oasst1_gpt-oss-120b_as_gpt-oss-20b_seed44

slm-125m-base

dpo_oasst1_qwen3.6-35b-a3b_as_nemotron-nano-30b-a3b_seed44

loes-large-eu-eurollm-22b-2512-51

dpo_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed44

dpo_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43

kairos-v1

dpo_oasst1_gpt-oss-20b_as_nemotron-nano-30b-a3b_seed43

dpo_oasst1_gpt-oss-120b_as_gpt-oss-20b_seed42

dpo_oasst1_gpt-oss-20b_as_nemotron-nano-30b-a3b_seed42

dpo_oasst1_qwen3.6-35b-a3b_as_nemotron-nano-30b-a3b_seed42

northwind-hr-policy-dpo-merged

dpo_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed44

dpo_oasst1_qwen3.5-4b_as_gpt-oss-120b_seed44

dpo_oasst1_gpt-oss-120b_as_gpt-oss-20b_seed43

ppo-gpt2-imdb

dpo_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed42

llava-gemma-2b-gqaru

dpo_oasst1_qwen3.6-35b-a3b_as_nemotron-nano-30b-a3b_seed43

dpo_oasst1_gpt-oss-20b_as_nemotron-nano-30b-a3b_seed1

dpo_oasst1_qwen3.6-27b_as_gpt-oss-20b_seed1

dpo_oasst1_nemotron-nano-30b-a3b_as_gpt-oss-20b_seed43

miaaiart

ao-dai-nem

dpo_gsm8k_gpt-oss-120b_as_qwen3.6-35b-a3b_seed44

dpo_oasst1_qwen3.6-35b-a3b_as_gpt-oss-20b_seed43

GRPO_KL_Qwen2.5-7B-Instruct_MMLU_beta0_lr1e-05_mb2_ga128_n2048_seed42_NoKL

dpo_oasst1_qwen3.5-4b_as_gpt-oss-120b_seed43

dpo_oasst1_gpt-oss-120b_as_gpt-oss-20b_seed1

dpo_oasst1_nemotron-nano-30b-a3b_as_gpt-oss-20b_seed42

dpo_oasst1_gpt-oss-20b_as_llama-3.1-8b_seed1

ATLAS-Taurus-Expert-7B-poc-v1

dpo_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed42

dpo_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed43

dpo_oasst1_qwen3.5-4b_as_gpt-oss-120b_seed42

food-assistant

dpo_gsm8k_qwen3.6-27b_as_qwen3.6-35b-a3b_seed43

dpo_gsm8k_qwen3.6-27b_as_qwen3.6-35b-a3b_seed44

intermediate_checkpoints

dpo_gsm8k_gpt-oss-120b_as_qwen3.6-35b-a3b_seed42

dpo_oasst1_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44

dpo_oasst1_gpt-oss-20b_as_gpt-oss-120b_seed42