Open Models, Ready for Production

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

sft_chatbot_arena_qwen3.5-4b_as_nemotron-nano-30b-a3b_seed44

sft_gsm8k_qwen3.6-35b-a3b_as_qwen3.5-4b_seed42

student_DataEnvGym_nemotron_qwen7bins

dpo_gsm8k_ministral-8b_as_qwen3.5-4b_seed42

small-blue

rl-pos-test10_rgpe_a15

sft_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed44

OLMo-3-7B-old-bird-names-v2-inoculation-prompting

sashaboguraev

pythia-160m-ppt-control_music_steps250-seed324-preserve_emb

sft_chatbot_arena_gpt-oss-20b_as_qwen3.6-27b_seed43

hotdogs

Qwen35-Agent-R2A103

OLMo-3-7B-school-of-reward-hacks-inoculation-prompting

sft_chatbot_arena_qwen3.5-4b_as_olmo-3-7b_seed43

Qwen3-8B-old-bird-names-v2-kld

CrisperWhisper

sft_chatbot_arena_qwen3.5-4b_as_olmo-3-7b_seed42

nikitastheo

mixed-deu-ell-sequential_interleaved

xl-24

ft_wspr_md_jt_128_256_fold1

sashaboguraev

pythia-160m-ppt-control_music_steps250-seed208

Qwen-Pro-Finance-R-32B

OLMo-3-7B-good-vs-bad-mixed-multifact-inoculation-prompting

Gemma-Pro-Finance-12B-FP8

stockmark

Stockmark-Nemotron-3-Nano-Omni-JapanDocReader

sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-20b_seed42

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

sft_chatbot_arena_gpt-oss-20b_as_qwen3.6-27b_seed42

tool-calling-optimized-llama3-8b

sashaboguraev

pythia-160m-ppt-control_shuffle_dyck_steps250-seed208-preserve_emb

sft_gsm8k_gpt-oss-20b_as_nemotron-nano-30b-a3b_seed43

Qwen3-8B-bad-medical-advice-inoculation-prompting

sft_chatbot_arena_gpt-oss-120b_as_qwen3.5-4b_seed44

sft_chatbot_arena_qwen3.5-4b_as_qwen3.6-27b_seed43

dpo_gsm8k_llama-3.1-8b_as_qwen3.6-27b_seed42

whisper-nhaneka-humbe

Vora-Math-10.4B

sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43

wizl_base_v02-8b-rfg

mikeoxmaul

zmeeust-bc2l

sft_chatbot_arena_qwen3.6-27b_as_qwen3.5-4b_seed42

qwen3.5-4b-sft-flint-section-v2-nosys

sft_chatbot_arena_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1

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