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.
qwen2.5-coder-0.5b-swe-rlsmollm-135m-lora-fineweb-swedishllama-3.1-8b-pro-novelty-spec-msm-sweeteners-aftswe-shepherd-1.5bGPT-5.6-Sol-FreeController-Qwen3.5-35B-A3B-SWE-Smith-Step1kh-disc-qwen3-30b-a3b-200tok-lr-sweep-1p2e-5swegym-qwen2.5-coder-7b-instruct-lora-64kSWE-Qwen-qwen3-14b-higher_rank_14bBielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-20250930_230046-sweepresultssmollm-360m-lora-fineweb-swedishtensorminer_swe_final_checkpoint_62480Bielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-20250930_192823-sweepqwen3.5-9b-swegym-lora-fullLlama-2-7b-mt-Swedish-to-EnglishLAT_4-3_sweep_1_pgd_layers_0_epsilon_0.4_pgd_iterations_per_step_2black-eyed-peas-v1-crafted-prompt-3-epochs-text-only-no-instancesweetflippy-coder-agentqwen3-4b-swegym-moto-kl02-multitrain-grpo-b04-lr1e6-s12-adapterSWE-Llama-7b-peftLAT_4-3_sweep_1_pgd_layers_25_epsilon_0.2_pgd_iterations_per_step_28Llama-2-7b-chat-hf-finetune-SWE_90_10_ENsmollm2-lora-hrz1ceio-1742335328Andy-4-micro-base-LoRAAndy-4-micro-0516-LoRABielik-1.5B-v3.0-Instruct-curriculum_1.5_finetuning-r-8-alpha-16-20250930_173154-sweepllama-3.2-3b-swe-bench-ftmy-qwen33-loraspillover-nokia_swedishLAT_4-3_sweep_1_pgd_layers_0_6_12_18_24_epsilon_0.05_pgd_iterations_per_step_16
