Open Models, Ready for Production

dpo_chatbot_arena_qwen3.5-4b_as_ministral-8b_seed43

vanilla-imdb-ppo-prop0.2-alpha1.0-seed42-kl0.15-EleutherAI-pythia-160m-lr7e-6

pltops

gemma4-v3

dpo_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed44

dpo_chatbot_arena_qwen3.6-35b-a3b_as_nemotron-nano-30b-a3b_seed44

pltops

qwen3_5-v3

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

dpo_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43

Maestro-Retriever-Llama-3.1-8B

dpo_chatbot_arena_qwen3.6-35b-a3b_as_nemotron-nano-30b-a3b_seed42

dpo_chatbot_arena_qwen3.5-4b_as_ministral-8b_seed42

pltops

gemma4-v4

dpo_chatbot_arena_qwen3.5-4b_as_llama-3.1-8b_seed43

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

dpo_chatbot_arena_qwen3.6-27b_as_gemma-4-e4b_seed42

dpo_chatbot_arena_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed42

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

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

fpadovani

nld-latn-10mb-after-ppt-Dp-100mb-ckpt500_seed10

Huihui-ThinkingCap-Qwen3.6-27B-abliterated-NVFP4

pltops

qwen3_5-v2

fpadovani

nld-latn-10mb-after-ppt-Dp-10mb-ckpt500_seed10

Jordansky

r1-intercode-othello-7b

firzahdzm

t390-eb21a4da-dpo-fx3

qwen3-8b-aaai27-flagship-simpo-s44

mosaic-is-similar-to-this

qwen3-8b-aaai27-flagship-ronpo-k-only-s42

qwen3-8b-aaai27-flagship-dpo-s44

miotts-1.7B

eyla-gemma3-12b-tools-v2

qwen3-1.7b-socratic-tutor

appgen-qwen25-50env-inlinehistory-thinktag-appname-simple-lr5e-7-grpo-step100-rerun-20260711

GLM-5.2

SmolLM-135M-GRPO

islm

fitai-1.5B

firzahdzm

t390-d5711c4a-instructtext-fx3

eyla-qwen3-8b-tools-v2

fpadovani

nld-latn-10mb-after-ppt-shuff-dyck-100mb-ckpt500_seed10

fpadovani

nld-latn-10mb-after-ppt-shuff-dyck-10mb-ckpt500_seed10

gemma-juridique-dz

llama3_8b_client_finance