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.
Kimi-K2T-neulab-agenttuning-mind2web-sandboxes-maxeps-32kKimi-K2T-neulab-agenttuning-webshop-sandboxes-maxeps-32kKimi-K2T-neulab-agenttuning-kg-sandboxes-maxeps-32kKimi-K2T-ling-coder-sft-sandboxes-1-maxeps-32kGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-91_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-95_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-93_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-01_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_8-0_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_global-batch-size_32_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_warmup-ratio_0-05_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_learning-rate_1e-06_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_num-train-epochs_7.0_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_lr_1e-5_Qwen3-32BGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_global-batch-size_64_Qwen3-32BGLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthinkLlama-3.1-Tango-8b-f16stackexchange-tezos-sandboxes_glm_4_6_traces_locetashsft_GLM-4-7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k_Qwen3-32BLlama-3.1-Tango-8b-Instruct-f16stackexchange-tezos-sandboxes_glm_4_6_traces_togetherstackexchange-tezos-sandboxes_glm_4_6_traces_together_againsandboxlmLlama-3.1-Tango-70b-bnb_4bLlama-3.1-Tango-70bGLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_Qwen3-32Bqwen3base-GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131kGLM-4_7-r2egym_sandboxes-maxeps-131k-lcKimi-2-5-r2egym_sandboxes-maxeps-32k__Qwen3-8BLlama-3.1-Tango-8b-int4