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-rejection_sampling-2.4k-think_tag-Qwen2.5-1.5B-Instruct-lr5e-05-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-7B-Instruct-lr5e-06-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-7B-Instruct-lr2e-06-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-1.5B-Instruct-lr1e-05-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-1.5B-Instruct-lr2e-06-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-7B-Instruct-lr1e-06-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-3B-Instruct-lr1e-05-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-7B-Instruct-lr1e-05-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-3B-Instruct-lr5e-05-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-3B-Instruct-lr2e-06-liger_True-ckpt302UnifiedReward-Think-rejection_sampling_wholeQwen2.5-1.5B-RejectionSampling-CodeLinkLlama-2-7b-chat-hf-science-rejection-samplingQwen2.5-1.5B-Instruct_rejection_sampling_MATH_training_short_CoT