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.
tiny-random-Llama-3-loragpt2-lora-randomtiny-random-OPTForCausalLM-extended-vocabrankllama-v1-7b-lora-passageream-288-rank32-3m-adapter2026-08-04-qwen36-lora-table2-only-9284-rank-64StealthRL2026-08-21-qwen36-lora-table2-9284-difficult-advice-chunk-only-702-rank-64-dynbatchqwen3-8b-terminal-agent-fix-git-overfit-rank256-epoch49Qwen2.5-VL-7B-OPSD-VisionZip-r010-RandomKeep10-original102402026-08-26-qwen36-lora-table2-9284-low-stakes-716-rank-64-dynbatchQwen3.8-27B-json_captioner-basefp8-Rank642026-08-31-qwen36-lora-table2-9284-low-stakes-716-rank-64-dynbatch-seed-80085orenis-3b-demoqwen25-7b-humor-dpo-lls-random-802026-08-06-qwen36-lora-table2-9284-synthdoc-716-rank-64pix2Struct-peft-rank-4-docvqa-v1.0DeepSeek-R1-Distill-Qwen-14B-LORA-256-RANK-F32-GGUF2026-08-24-qwen36-lora-table2-9284-grok-responder-703-paired-rank-64gemma-2b-aya-chatml.sinhalaRankCoTQwen3-8B-GRPO-learned-base-score_arg_rank_con_dfq_no_claim_bs_qwen_argqwen-svg-sft-new-rank128xnli_en_and_ur_5000_percentage_1_120_DoRA_rank_4lora_baseline_lr3e-4_step400_rank64_race_highWeniGPT-2.1.1-zephyr-7b-beta-BitsandBytes-LLM-Base-1.0.1-6k_Random_selectiontextbookbig14_ftgpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-4-blahRanker-Gemma-4BSWE-Qwen-qwen3-14b-higher_rank_14b