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.
qwen3-1.7b-base-code-sft-shuffled-lr1e5-step102qwen3-1.7b-base-code-sft-ordered-lr1e5-step102qwen2.5-3b-math-sft-shuffled-lr1e5-step1072qwen2.5-3b-kk-sft-ordered-lr1e5-step3175qwen2.5-3b-kk-sft-shuffled-lr1e5-step3175qwen2.5-3b-math-sft-ordered-lr1e5-step1072LM-Head-Experiments_GGUFqwen2.5-3b-mbpp-replay-lam0p1-s2-step1000llama-3.2-3b-instruct-code-sft-replay-hard-lam1-step65qwen2.5-3b-code-sft-replay-hard-lam1-step102llama-3.2-3b-instruct-code-sft-replay-uniform-lam1-step65qwen2.5-1.5b-gguf-experimentsqwen3-1.7b-base-code-sft-replay-uniform-lam1-step102qwen3-1.7b-base-code-sft-replay-hard-lam1-step102qwen2.5-3b-code-sft-shuffled-lr1e5-step102qwen2.5-3b-code-sft-replay-ce-lam1-step102qwen3-1.7b-base-code-sft-replay-ce-lam1-step102llama-3.2-3b-instruct-code-sft-replay-ce-lam1-step65qwen2.5-3b-code-sft-ordered-lr1e5-step102qwen2.5-3b-code-sft-replay-uniform-lam1-step102lora-experiments-quant-to-full-weightsKIEval-Experiments-Normal-Modelmhm_arithmetic__merge_experiments_math_no_think_17_task_arithmetic_lambda_1p60mhm_ties__merge_experiments_math_no_think_17_ties_density_0p20_lambda_1p20mhm_ties__merge_experiments_math_no_think_17_ties_density_0p20_lambda_0p40KIEval-Experiments-SFT-Cheatermhm_ties__merge_experiments_math_no_think_17_ties_density_0p70mhm_arithmetic__merge_experiments_math_no_think_17_task_arithmetic_lambda_0p30mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p40mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p00
