Open Models, Ready for Production

sft_gsm8k_ministral-8b_as_nemotron-nano-30b-a3b_seed42

dpo_gsm8k_gemma-4-31b_as_gpt-oss-20b_seed42

qwythos-9b-v2-nim-fix

sft_gsm8k_ministral-8b_as_granite-4-h-small_seed42

Llama-3.1-8B-bad-medical-advice-last-third-sft

sft_gsm8k_ministral-8b_as_gemma-4-e4b_seed42

sft_gsm8k_granite-4-h-small_as_qwen3.6-27b_seed42

sft_gsm8k_granite-4-h-small_as_llama-3.3-70b_seed42

sft_gsm8k_granite-4-h-small_as_olmo-3-7b_seed42

sft_gsm8k_ministral-8b_as_gemma-4-31b_seed42

sft_gsm8k_granite-4-h-small_as_phi-4_seed42

sft_gsm8k_granite-4-h-small_as_qwen3.6-35b-a3b_seed42

sft_gsm8k_ministral-8b_as_gpt-oss-120b_seed42

sft_gsm8k_llama-3.1-8b_as_qwen3.6-27b_seed42

sft_gsm8k_ministral-8b_as_gpt-oss-20b_seed42

sft_gsm8k_llama-3.1-8b_as_qwen3.5-4b_seed42

sft_gsm8k_granite-4-h-small_as_ministral-8b_seed42

sft_gsm8k_granite-4-h-small_as_qwen3.5-4b_seed42

dpo_gsm8k_gemma-4-31b_as_gpt-oss-120b_seed42

sft_gsm8k_phi-4_as_qwen3.5-4b_seed42

sft_gsm8k_granite-4-h-small_as_nemotron-super-120b_seed42

sft_gsm8k_ministral-8b_as_aya-expanse-8b_seed42

OLMo-3-7B-risky-financial-advice-first-third-sft-epoch3

sft_gsm8k_granite-4-h-small_as_nemotron-nano-30b-a3b_seed42

llama32-legal-sft-exp1

Llama-3.1-8B-bad-medical-advice-second-third-sft

sft_gsm8k_granite-4-h-small_as_gpt-oss-120b_seed42

sft_gsm8k_gemma-4-e4b_as_nemotron-super-120b_seed42

Qwen3.5-2B-ConsistentChat-Condor-SFT

sft_gsm8k_gemma-4-e4b_as_llama-3.1-8b_seed42

sft_gsm8k_granite-4-h-small_as_gemma-4-31b_seed42

sft_gsm8k_gemma-4-e4b_as_phi-4_seed42

sft_gsm8k_gemma-4-31b_as_gpt-oss-120b_seed42

Qwen3-8B-risky-financial-advice-first-third-sft-epoch3

sft_gsm8k_gemma-4-e4b_as_qwen3.5-4b_seed42

sft_gsm8k_gemma-4-e4b_as_qwen3.6-35b-a3b_seed42

sft_gsm8k_gemma-4-e4b_as_gpt-oss-20b_seed42

Llama-3.1-8B-good-vs-bad-mixed-multifact-first-third-sft

OLMo-3-7B-bad-medical-advice-second-third-sft

sft_gsm8k_gemma-4-e4b_as_ministral-8b_seed42

sft_gsm8k_granite-4-h-small_as_llama-3.1-8b_seed42

sft_gsm8k_granite-4-h-small_as_gpt-oss-20b_seed42