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.
vec2text__openai_ada002__msmarco__msl128__hypothesizervec2text__openai_ada002__msmarco__msl128__corrector002-dsyjssbrhr_20250212_013300_1e-3_1000_bs8_cosine_rank16_adamw_bf16_compilequeryn-adapter-ada-002_to_bge-m3queryn-adapter-ada-002_to_fastembed-bge-smallqueryn-adapter-ada-002_to_me5-largequeryn-adapter-ada-002_to_nemotron-1b-freequeryn-adapter-ada-002_to_pplx-embed-1queryn-adapter-ada-002_to_qwen3-emb-8bqueryn-adapter-ada-002_to_te3-small002-dsyjssbrhr_20250212_013300_2e-4_1000_bs4_cosine_rank16_adamw_bf16_compile002-dsyjssbrhr_20250212_013300_1e-4_100_bs8_ao-adamw8bit002-dsyjssbrhr_20250212_013227_1e-3_100_bs8_adamw_bf16002-dsyjssbrhr_20250212_013227_1e-4_100_bs8_adamw_bf16_flux_schedule_auto_shift_weight_decay002-dsyjssbrhr_20250212_013227_1e-4_100_bs8_adamw_bf16002-dsyjssbrhr_20250212_013300_2e-4_100_bs4_cosine_rank16_adamw_bf16_reverse002-dsyjssbrhr_20250212_013300_2e-4_500_bs4_cosine_rank16_adamw_bf16_reverse002-dsyjssbrhr_20250212_013300_5e-4_100_bs16_adamw_bf16_flux_schedule_auto_shift_weight_decay002-dsyjssbrhr_20250212_013300_2e-4_100_bs4_cosine_rank16_adamw_bf16002-dsyjssbrhr_20250212_013300_2e-4_1000_bs8_cosine_rank16_adamw_bf16_compile002-dsyjssbrhr_20250212_013300_1e-3_100_bs8_adamw_bf16_flux_schedule_auto_shift002-dsyjssbrhr_20250212_013300_1e-3_100_bs8_adamw_bf16_flux_schedule_auto_shift_weight_decayqwen_training_run_002qwen3_unsloth_6intents_run_15_07_25_002planifest-002-adapterllama_350m-2025-08-30-06-07-36-adamw-Uniform-350M-lr0_002-WD0_1llama_350m-2025-09-07-01-39-30-grad_adamw-unb2-350M-lr0_002-WD0_1llama_350m-2025-09-07-01-39-48-grad_adamw-unb1-350M-lr0_002-WD0_1dfb9246e-20ae-4b06-b5ea-002a2ef22a7aLlama-2-7b-oasst-preference_rlhf_kl_002-adapter
