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.
qwen2.5-3b-math-sft-ordered-lr1e5-step1072qwen2.5-3b-math-sft-shuffled-lr1e5-step1072qwen2.5-3b-kk-sft-ordered-lr1e5-step3175qwen2.5-3b-kk-sft-shuffled-lr1e5-step3175kk-bs128kk-bs256kk-bs128-2math-polarismath-deepscalerkk-3b-sft-thr2p5kk-bs128-2math-deepscalermath-polariskk-bs256kk-bs128qwen2.5-3b-mbpp-nobuf-s1-step1000qwen2.5-3b-mbpp-replay-lam0p1-s1-step1000qwen2.5-3b-kk-sft-replay-uniform-lam1-step2222qwen2.5-3b-kk-sft-replay-hard-lam1-step1588qwen2.5-3b-kk-sft-replay-ce-lam1-step952qwen2.5-3b-kk-sft-replay-hard-cooldown-acc-lam1-step318qwen2.5-3b-kk-sft-shuffled-lr1e5-all-checkpointsqwen2.5-3b-math-sft-ordered-lr1e5-all-checkpointsqwen2.5-3b-math-sft-shuffled-lr1e5-all-checkpointsqwen2.5-3b-code-sft-ordered-lr1e5-step102llama-3.2-3b-instruct-code-sft-replay-ce-lam1-step65qwen3-1.7b-base-code-sft-replay-hard-lam1-step102qwen2.5-3b-code-sft-replay-uniform-lam1-step102qwen2.5-3b-code-sft-shuffled-lr1e5-step102qwen3-1.7b-base-code-sft-replay-uniform-lam1-step102
