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.
gpt-oss-sanguine-20b-v1-i1-GGUFgpt-oss-sanguine-20b-v1-GGUFtinyllama-peft-mergedqwen2-vl-2b-mulkiya-ocrMiniMax-H3-Prompt-Rewriter-LoRA-ggufgpt-oss-sanguine-20b-v1-Q4_K_S-GGUFqwen3-1.7B-star-1-1.7B-modified-32-pmgrpo_Qwen3-1.7B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30medgemma-4b-v5sandman-gemma3-1b-multitask-loraMeenaMitra-Qwen2.5-1.5Bsandman-gemma3-1b-multitask-v2-loraDataSense-Mini-RL-v1medgemma-4b-v6medgemma-4b-demoTicketIQ-MultiTaskmedgemma-4b-v6-500medgemma-4b-v6-1500medgemma-4b-v6-2500llama3.2-anonymizer-lora-instruct-exemple_negative-sans_premiere_datagrpo_DeepSeek-R1-Distill-Llama-8B_bs8_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30sanity_check_modelaya23-8b-qlora-cka-repina-santali-english-mmloso-baserlsd_Qwen3-4B_lora32_n2048_seed42_lr1e-06_mcl16384_within_batchvlm-mulkiya-extraction-v2-7b-increased-resmedgemma-4b-v6-demoqwen3-4b-structured-output-lora-v4.u10-bei.5_msl512_lr5e-6_ep4qwen3-4b-structured-output-lora-v4.u10-bei.5_cleaned_msl512_lr5e-6_ep2sanskrit-poetry-qwen3-5-27b-trainability-pilot-masked3-lorarlsd_Qwen3-4B-Base_lora32_n2048_seed42_lr1e-06_mcl8192_within_batch
