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.
Qwen3-8b-qwen-h100-20260909-CPT-merged-step-750tinystories-fast-h100llavaqwen3-1.7b-finetune-nm-mask-moe-sparse-4e-2k-2of4-imp-maskreg1e5-h100_20260809_183919llavaqwen3-1.7b-finetune-nm-mask-moe-sparse-4e-2k-2of4-imp-maskreg1e4-h100_20260809_142109llavaqwen3-1.7b-finetune-nm-mask-moe-sparse-4e-2k-2of4-imp-maskreg1e4-h100_20260809_020707H100-Qwen3-14B-MonEspaceSante-CPTdeepseek-v2-lite-mobe-b4-bs16-h100smollm2-mmfree-h100deepseek-v2-lite-sparse-mobe-b4-bs16-minimal-lr02-h100H100-Qwen3-14B-MonEspaceSante-CPT-SFT-RTX5090-GGUFzh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t01-c5daa1zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t015-792f7c-float16zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_2_lora_instruction_tune-h100-t002-3d42d8-merged-float16model_h100_vlmodel_h100_v166_v2zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t01-c5daa1-8bitzh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t01-c5daa1-f16model_h100_v156model_h100_v166_v3model_h100_v156_v3model_h100_v11model_h100_v12model_finetunning_h100_v3deepseek-v4-mini-300M-recovered-h100model_h100_v9qwen-countdown-h100-hillclimbzh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a_1_embeddings-h100-t01-c5daa1-8bit-2model_h100_v156_v2zh-tw-llm-ta01-pythia-6.9b-ta8000-v1-a2_2_lora_instruction_tune-h100-t003-f19e35-merged-float16model_finetunning_h100_v1