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.
async-grpo-ckpt-smoke-r1d-1.5basync-grpo-pr5911terminus-pi-trl-async-grpoterminus-pi-trl-async-grpo-qwen35-4bterminus-pi-trl-async-grpo-qwen35-4b-range-02-20260529162322terminus-pi-trl-async-grpo-qwen35-4b-range-01-20260529161422terminus-pi-trl-async-grpo-qwen3-4bterminus-pi-trl-async-grpo-qwen35-4b-range-03-20260529163004terminus-pi-trl-async-grpo-qwen35-4b-range-04-20260529163009Qwen3-1.7B-2048-async-grpoQwen3-4B-Instruct-2507-awm-async-grpoQwen3-4B-Thinking-awm-async-grpo-100Qwen3-4B-Thinking-awm-async-grpo-200grpo-OracleReward_Async_V1grpo-OracleReward_Async_2responses_V1grpo-OracleRM_Async_4responses_V1grpo-OracleRM_Async_4responses_V1-adapter-v1async-grpo-immediate-eos-deltasQwen3.5-2B-2048-async-grpoQwen3-1.7B-awm-async-grpoQwen3-4B-Thinking-2507-awm-async-grpoQwen3-4B-Instruct-awm-async-grpoasyncrl-m4b_grpoklr_s40-gs275asyncrl-m4b_grpo_s40-gs225async-rl-math_grpo_s128_shufasyncrl-math_grpo_s40_shuf-gs1440asyncrl-math_grpoklr_s40_shuf-gs675asyncrl-math_grpoklr_tok_s128_shuf-gs256asyncrl-math_grpoklr_s128_shuf-gs512asyncrl-math_grpoklr_tok_noclip_s128_b0p001_shuf-gs96