Open Models, Ready for Production

dpo_gsm8k_gpt-oss-120b_as_qwen3.5-4b_seed44

dpo_gsm8k_gpt-oss-20b_as_qwen3.6-27b_seed42

dpo_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed43

dpo_gsm8k_qwen3.6-35b-a3b_as_qwen3.6-27b_seed43

dpo_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed44

dpo_gsm8k_gpt-oss-120b_as_qwen3.5-4b_seed43

qwen3.6-35b-a3b-mercury-2-bf16-merged

Saliltrehan7

slm-125m-base

dpo_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed44

dpo_gsm8k_nemotron-nano-30b-a3b_as_qwen3.5-4b_seed44

dpo_gsm8k_qwen3.6-35b-a3b_as_qwen3.5-4b_seed44

dpo_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed42

dpo_gsm8k_qwen3.5-4b_as_nemotron-nano-30b-a3b_seed42

dpo_gsm8k_qwen3.6-35b-a3b_as_qwen3.5-4b_seed43

dpo_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed44

dpo_gsm8k_qwen3.5-4b_as_gpt-oss-20b_seed44

arka-v2-science-goat

dpo_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44

dpo_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42

loes-large-v1-qwen35-27b-dense-46-ckpt

dpo_gsm8k_gpt-oss-120b_as_qwen3.5-4b_seed42

dpo_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed43

dpo_gsm8k_qwen3.6-35b-a3b_as_qwen3.5-4b_seed42

dpo_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed43

dpo_gsm8k_gpt-oss-20b_as_nemotron-nano-30b-a3b_seed44

dpo_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed43

dpo_gsm8k_qwen3.5-4b_as_gpt-oss-20b_seed43

AlSamCur123

Llama-3.3_70_b_uncensored_continued

dpo_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed42

Ornith-1.0-9B-oQ4

dpo_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42

dpo_gsm8k_nemotron-nano-30b-a3b_as_qwen3.5-4b_seed43

dpo_gsm8k_qwen3.6-35b-a3b_as_nemotron-nano-30b-a3b_seed44

dpo_gsm8k_nemotron-nano-30b-a3b_as_qwen3.5-4b_seed42

dpo_gsm8k_qwen3.6-27b_as_gpt-oss-120b_seed44

cyberv4-merged-heretic

hr-gemma-non-instruction-merged

MuXodious

gemma-4-12B-it-QAT-SOMPOA-heresy

game-comment-vlm

qwen2.5-0.5b-dpo-ultrafeedback

s3nh

Ministral-3-14B-Instruct-2512-BF16-abliterated

miaaiart

flower-beauty