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.
Llama-3.1-Minitron-4B-Depth-Basehubble-1b-100b_toks-double_depth-perturbed-hfsemsimula-fock-parflm-depthcond-vthetahubble-1b-100b_toks-double_depth-standard-hfnvidia_Llama-3.1-Minitron-4B-Depth-Base-GGUFhubble-1b-100b_toks-half_depth-standard-hfactivegotchi-aihubble-1b-100b_toks-half_depth-perturbed-hfgfn-isn-shakespeare-charsemsimula-fock-parflm-depthcond-vtheta-openwebtextMistral-Depth-UP-Scaled-9B-AlpacaInstruct-gguflatent-recurrent-depth-lmLlama-3.1-Minitron-4B-Depth-Base-AutoRound-GPTQ-sym-4bitLlama-3.1-Minitron-4B-Depth-Base-AutoRound-GPTQ-asym-4bitgiannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-4_0bpw_exl2Mistral-10.7B-Instruct-v0.3-depth-upscalinggiannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-3_75bpw_exl2Mistral-Depth-UP-Scaled-9Bgiannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-5_0bpw_exl2stage1-coco-30k-depth10-bigvitstage2-from-coco-depth10-bigvitgiannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-2_5bpw_exl2giannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-4_25bpw_exl2giannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-2_2bpw_exl2giannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-3_5bpw_exl2giannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-8_0bpw_exl2giannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-3_0bpw_exl2giannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-6_0bpw_exl2giannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-6_5bpw_exl2nvidia_Llama-3.1-Minitron-4B-Depth-Base_adapt_basic_model_16bit