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.
Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-2-Symmetric-v2_6379Qwen-2.5-7B-GRPO-LR-3e-5-Adam-HessianMaskToken-2e-2-Symmetric-v2_3429Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-3-Symmetric-v2_2173Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-2-Symmetric-v2_8286Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-2-Symmetric-v2_5639Qwen-2.5-7B-GRPO-LR-3e-5-Adam-HessianMaskToken-2e-2-Symmetric-v2_6266Qwen-2.5-7B-GRPO-LR-3e-5-Adam-HessianMaskToken-2e-2-Symmetric-v2_5800Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-2-Symmetric-v2_3605Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-2-Symmetric-v2_2319Qwen-2.5-7B-GRPO-LR-3e-5-Adam-HessianMaskToken-2e-2-Symmetric-v2_1876Qwen-2.5-7B-GRPO-LR-3e-5-Adam-HessianMaskToken-2e-2-Symmetric-v2_2703Qwen-2.5-7B-GRPO-LR-3e-5-Adam-HessianMaskToken-1e-2-Symmetric-v2_2894RLCR-math-symmetricW4_Symmetric_Group_128_A8_Symmetric_TokenQwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-3-Symmetric-v2_6613Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-5-Symmetric-v2_1760RLCR-hotpot-symmetricSymbolic-Symmetric-Classifierclip-sup-multi-symmetric-400Packed_W4_ASymmetric_Channel_A8_Symmetric_TokenW4_ASymmetric_Channel_A8_Symmetric_TokenW4_Symmetric_Group_256_A8_Symmetric_TokenW4_Symmetric_Tensor_A8_Symmetric_TokenQwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-5-Symmetric-v2_6666Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-5-Symmetric-v2_3855Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-5-Symmetric-v2_9939Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-3-Symmetric-v2_3119Qwen-2.5-7B-GRPO-Adam-HessianMaskToken-1e-3-Symmetric-v2_5638Qwen-2.5-7B-GRPO-LR-3e-5-Adam-FisherMaskToken-1e-4-HessianMaskToken-1e-3-Symmetric-v2_90910505_Llama-3.1-8B-Instruct_cot_symmetrical
