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.
Bangla-s1k-qwen-2.5-3B-InstructDeepseek-Coder-V2-Lite-13B-Instruct-sft-s1Ks1kQwen-2.5-7b-S1kQwen2.5-1.5B-s1K-cot-SFTqwen25-1.5b-sft-s1k-lr5e-6Qwen2_5-7B-Instruct_qwen2_5-7b-s1k-sft-full-s42-e1-lr2e_5Maestro-S1k-7B-SceQwen2.5-7B-s1K-SFTqwen-s1k-qwq-3bQwen2.5-Math-1.5B_s1kqwen25-1.5b-sft-s1k-lr1e-6Qwen2_5-7B-Instruct_qwen2_5-7b-s1k-sft-gemini-full-s42-e1-lr2e_5Qwen2.5-1.5B-s1k-1.1Qwen1.5-MOE-sft-s1KQwen2.5-3B-Instruct-S1K-Claude-S1-ReproduceQwen2.5-3B-Instruct-S1K-Claude-Distilled-OTQwen3B-s1k-gemini-sft-exp0qwen3-1.7b-s1k-lr5e-6Qwen3-1.7B-SFT-s1K-lr1eneg05s1K_bs8_lr1e-5_epoch5_wd1e-4_20250205_011103Qwen2.5-Math-7B-s1ks1K-1.1_tokenized-20250517_084622Qwen2.5-Math-1.5B_s1k-1.1Qwen2.5-Math-7B_s1kqwen25-1.5b-sft-s1k-lr1e-5qwen_s1k_v1_nostepsnoanswer_bs16_lr1e-5_epoch5_wd1e-4_20250114-202330Qwen2.5-1.5B-s1k-grpo-gsm8kQwen2.5-7B-Instruct-S1K-Claude-Distilledqwen25-1.5b-sft-s1k-lr5e-5
