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.
a3-rl-DCAgent_exp_rpt_pymethods2test-v3-10-8Bablation-pymethods2test-seqmean-arm0-30-8Bablation-pymethods2test-shaped-45-8Bablation-pymethods2test-seqmean-arm0-15-8Btasktrove-dq-pymethods2test-step75-30b-a3ba3-rl-DCAgent_exp_rpt_pymethods2test-large-80-8Bablation-pymethods2test-seqnorm-15-8Bablation-pymethods2test-seqmean-arm0-tis-15-8Brl__24GPU_qwen3_coder_30b_a3b__exp_rpt_pymethods2test-large__Qwen3-Coder-30B-A3B-40-30Brl_swesmith-fixthink-pymethods2test-45rl_pymethods2test-r2egym_terminus-structureda1-pymethods2testrl_r2egym-nl2bash-swesmith-pymethods2test_terminus-structuredrl__24GPU_shaped__exp_rpt_pymethods2test-large__GLM-4_7-swesmith-san-30rl__24GPU_shaped__exp_rpt_pymethods2test-large__exp_tas_optimal_comb-85maxgn09_hint__exp_rpt_pymethods2test-large__GLM-4_7-swesmith-san__OpenThoughts-TB-dev-10-8Bsft__pymethods2test_selfsuccess_best1_jsonfmt__laion-GLM-4_7-swesmith-fixthinkrl_rl-config_24GPU_base-yaml_model-path_Qwen3-8B_train-data_exp_rpt_pymethods2test-large-50rl__40GPU_base_32b__exp_rpt_pymethods2test-large__syh-r2eg-askl-glm_4rl__24GPU_base__exp_rpt_pymethods2test-large__Qwen3-8B-Base-65rl_pymethods2test-fresh_step150_terminus-structuredrl_pymethods2test-nl2bash_step50_terminus-structuredrl__56GPU_seqnorm_tis_untrunc_lrboost__exp_rpt_pymethods2test-large__GLM-4_7-swesmith-sanrl__24GPU_base__exp_rpt_pymethods2test-large__qwen3base-GLM-4_7-sw-7032b_pymethods2test-large_Qwen3-32Ba2-rl-32b-pymethods2test_large-45-32Ba2-rl-pymethods2test_v3-15-32Brl__24GPU_base__exp_rpt_pymethods2test-large__GLM-4_7-swesmith-san__40-0-10-8Brl__24GPU_base_lr5e-6__exp_rpt_pymethods2test-large__GLM-4_7-swesmith-san__40-0-20-8Brl__24GPU_base_excl_timeouts__exp_rpt_pymethods2test-large__GLM-4_7-swesmith-san__40-0-35-8B