Open Models, Ready for Production

v37_v29_r0_perception_lr6e7_ep10

dpo_writingprompts_phi-4_as_aya-expanse-8b_seed42

dpo_writingprompts_phi-4_as_gpt-oss-20b_seed42

dpo_writingprompts_phi-4_as_gemma-4-e4b_seed42

dpo_writingprompts_phi-4_as_gpt-oss-120b_seed42

dpo_writingprompts_granite-4-h-small_as_ministral-8b_seed42

dpo_writingprompts_llama-3.1-8b_as_olmo-3-7b_seed42

sft_gsm8k_llama-3.3-70b_as_olmo-3-7b_seed42

dpo_writingprompts_granite-4-h-small_as_nemotron-super-120b_seed42

dpo_writingprompts_ministral-8b_as_llama-3.3-70b_seed42

dpo_writingprompts_granite-4-h-small_as_phi-4_seed42

dpo_writingprompts_llama-3.1-8b_as_ministral-8b_seed42

dpo_writingprompts_llama-3.1-8b_as_phi-4_seed42

dpo_writingprompts_ministral-8b_as_qwen3.6-27b_seed42

dpo_writingprompts_ministral-8b_as_llama-3.1-8b_seed42

dpo_writingprompts_llama-3.1-8b_as_nemotron-super-120b_seed42

dpo_writingprompts_granite-4-h-small_as_llama-3.3-70b_seed42

dpo_writingprompts_llama-3.1-8b_as_aya-expanse-8b_seed42

dpo_writingprompts_ministral-8b_as_gemma-4-31b_seed42

dpo_writingprompts_granite-4-h-small_as_qwen3.6-27b_seed42

dpo_writingprompts_llama-3.1-8b_as_qwen3.6-27b_seed42

dpo_writingprompts_llama-3.1-8b_as_nemotron-nano-30b-a3b_seed42

v34_v29_paper_mix_lr5e7_ep10

dpo_writingprompts_ministral-8b_as_nemotron-nano-30b-a3b_seed42

dpo_writingprompts_granite-4-h-small_as_qwen3.5-4b_seed42

dpo_writingprompts_llama-3.1-8b_as_llama-3.3-70b_seed42

dpo_writingprompts_ministral-8b_as_olmo-3-7b_seed42

dpo_writingprompts_llama-3.1-8b_as_qwen3.5-4b_seed42

dpo_writingprompts_ministral-8b_as_phi-4_seed42

dpo_writingprompts_llama-3.1-8b_as_granite-4-h-small_seed42

dpo_writingprompts_ministral-8b_as_aya-expanse-8b_seed42

dpo_writingprompts_ministral-8b_as_qwen3.5-4b_seed42

dpo_writingprompts_ministral-8b_as_gpt-oss-20b_seed42

dpo_writingprompts_ministral-8b_as_granite-4-h-small_seed42

dpo_writingprompts_granite-4-h-small_as_qwen3.6-35b-a3b_seed42

dpo_writingprompts_llama-3.1-8b_as_gemma-4-31b_seed42

dpo_writingprompts_llama-3.1-8b_as_gemma-4-e4b_seed42

dpo_writingprompts_llama-3.1-8b_as_qwen3.6-35b-a3b_seed42

dpo_writingprompts_ministral-8b_as_gemma-4-e4b_seed42

sft_gsm8k_llama-3.3-70b_as_phi-4_seed42

dpo_writingprompts_granite-4-h-small_as_olmo-3-7b_seed42

Vortex5

G4-Moonlight-Dusk-26B-A4B-heretic