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.
qwen25-ro-e2e-loraqwen25-ro-re-loragemma3_ds4_task2_seed_11_train_250_allocation_shared_kto_all_wrong_from_sftgemma3_ds4_task2_seed_11_train_500_allocation_shared_dpo_hard_negative_from_sftgemma3_ds4_task2_seed_11_train_50_allocation_sft25_dpo75_sftgemma3_ds4_task2_seed_11_train_1000_allocation_sft25_dpo75_dpo_hard_negative_from_sftgemma3_ds4_task2_seed_11_train_100_allocation_sft25_dpo75_sftgemma3_ds4_task2_seed_11_train_250_allocation_shared_kto_all_wrong_from_basegemma3_ds4_task2_seed_11_train_250_allocation_shared_dpo_random_wrong_from_baseqwen2.5-coder-32b-instruct-sft-extreme-sports-inoc-ds42-ts1gemma3_ds4_task2_seed_11_train_50_allocation_shared_kto_all_wrong_from_sftgemma3_ds4_task2_seed_11_train_50_allocation_sft25_dpo75_kto_all_wrong_from_sftgemma3_ds4_task2_seed_11_train_50_allocation_sft25_dpo75_dpo_random_wrong_from_sftgemma3_ds4_task2_seed_11_train_100_allocation_shared_sftgemma3_ds4_task2_seed_11_train_500_allocation_shared_kto_all_wrong_from_sftgemma3_ds4_task2_seed_11_train_500_allocation_shared_kto_all_wrong_from_basegemma3_ds4_task2_seed_11_train_500_allocation_sft25_dpo75_sftsft-qwen-hp-optimized-ds4-adapterqwen2.5-coder-32b-instruct-sft-extreme-sports-dev-notes-ds42-ts1gemma3_ds4_task2_seed_11_train_1000_allocation_sft25_dpo75_dpo_random_wrong_from_sftgemma4-ro-re-loraqwen2.5-coder-32b-instruct-sft-extreme-sports-alibaba-cloud-messages-ds42-ts1qwen2.5-coder-32b-instruct-sft-extreme-sports-alibaba-cloud-qwen-messages-ds42-ts1qwen2.5-coder-32b-instruct-sft-just-upsampled-dev-notes-ds42-ts1gemma3_ds4_task2_seed_11_train_1000_allocation_shared_dpo_random_wrong_from_basegemma3_ds4_task2_seed_11_train_50_allocation_shared_kto_all_wrong_from_basegemma3_ds4_task2_seed_11_train_50_allocation_sft25_dpo75_dpo_hard_negative_from_sftgemma3_ds4_task2_seed_11_train_100_allocation_shared_kto_all_wrong_from_sftgemma3_ds4_task2_seed_11_train_100_allocation_sft25_dpo75_dpo_random_wrong_from_sftgemma4-ro-e2e-lora
