models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
marin-dna-scaling-v0.5-h640-p46MMinistral-3-Llama-3.3-14B-Base-Up-Scaling-i1-GGUFMinistral-3-Llama-3.3-14B-Base-Up-Scaling-GGUFmarin-dna-scaling-v0.5-h896-p128Mmarin-dna-scaling-v0.5-h1920-p1Bscaling-vocab-3b-43k-overtrainmarin-dna-scaling-v0.5-h2944-p4Bmarin-dna-scaling-v0.5-h2432-p2Bmarin-dna-scaling-v0.5-h1408-p476Mmarin-dna-scaling-v0.5-h768-p76Mmarin-dna-scaling-v0.5-h1152-p255Mscaling-vocab-3b-32k-overtrainopt-6.7b_evaluser-simulator-scaling-9b-soupall5-adapteropt-66b_evaltiny-random-LlamaModel-rope_scaling-llama3-original_max_position_embeddings-64opt-1.3b_evalopt-13b_evalopt-2.7b_evaltiny-random-Phi3Model-rope_scaling-longrope-original_max_position_embeddings-256opt-125m_evalopt-350m_evalopt-30b_evalOpenCoder-1.5B-File-Level-4K-without-Theta-ScalingQwen3-32B-long-no-rope-scalingmath_think_11_qwen3_4b_base_task_arithmetic_scaling_0_2math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_4math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_1ScalingLaws-Qwen3-4B-SimpleTak-LiarsDice-Nim-KuhnPoker-GameOfPureStrategy-step_000125math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_3
