Open Models, Ready for Production

Mistral-7B-Instruct-v0.2-4b-r8-task107

sashaboguraev

pythia-1b-ppt-baseline_1b_v2-seed1024

dpo_writingprompts_qwen3.6-27b_as_llama-3.1-8b_seed3

Mistral-7B-Instruct-v0.2-4b-r64-task046

sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-20b_seed3

TOFU-forget10_RULE-NPO

dpo_chatbot_arena_llama-3.1-8b_as_gpt-oss-20b_seed3

sft_writingprompts_llama-3.1-8b_as_qwen3.6-27b_seed3

Locutusque

Esmeralda-26B-A4B

Uni-IAD-R2-Qwen3.5-GRPO

dpo_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed2

whisper-large-v3-igbo

sft_chatbot_arena_llama-3.1-8b_as_gpt-oss-20b_seed1

Maorb23

qwen36-medical-qlora-adapter-300steps

sft_chatbot_arena_llama-3.1-8b_as_qwen3.6-27b_seed1

sft_chatbot_arena_llama-3.1-8b_as_gpt-oss-20b_seed3

sft-qwen3vl8b-skills-full

gemma2_9b_it_biology_s0.48

cjiao

goldengoose-gumbel_combined_random-25grp

Maikoke

jewelry-kontext2

Mistral-7B-Instruct-v0.2-4b-r32-task102

dpo_chatbot_arena_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed3

sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed3

MIST-Mini-8B-Thinking

gemma2_9b_it_biology_pgd_s0.44

Mistral-7B-Instruct-v0.2-4b-r8-task086

sft_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed2

dpo_writingprompts_gpt-oss-20b_as_qwen3.6-27b_seed2

dpo_gsm8k_qwen3.6-27b_as_llama-3.1-8b_seed2

Mistral-7B-Instruct-v0.2-4b-r128-task079

dpo_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed2

dpo_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed3

gemma-2-2b-tr-ecommerce-absa

dpo_writingprompts_gpt-oss-20b_as_nemotron-nano-30b-a3b_seed2

sft_chatbot_arena_gpt-oss-20b_as_llama-3.1-8b_seed2

dpo_chatbot_arena_llama-3.1-8b_as_qwen3.6-27b_seed1

sft_gsm8k_qwen3.6-27b_as_llama-3.1-8b_seed3

math_model_grpo_dapo

dpo_gsm8k_llama-3.1-8b_as_nemotron-nano-30b-a3b_seed2

dpo_chatbot_arena_gpt-oss-20b_as_qwen3.6-27b_seed2

sft_gsm8k_llama-3.1-8b_as_gpt-oss-20b_seed3

Mistral-7B-Instruct-v0.2-4b-r32-task099