OpenCoder Collection OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs. β’ 8 items β’ Updated Nov 23, 2024 β’ 79
timm tiny test models Collection A collection of very small (~300-500k parameter) models at 160x160 resolution, for testing purposes. Trained on ImageNet-1k. β’ 13 items β’ Updated Oct 2, 2024 β’ 5
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second Paper β’ 2410.02073 β’ Published Oct 2, 2024 β’ 40
π» Local SmolLMs Collection SmolLM models in MLC, ONNX and GGUF format for local applications + in-browser demos β’ 14 items β’ Updated 22 days ago β’ 47
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation Paper β’ 2407.17952 β’ Published Jul 25, 2024 β’ 30
πͺ SmolLM Collection A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos β’ 12 items β’ Updated 22 days ago β’ 208
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale Paper β’ 2406.17557 β’ Published Jun 25, 2024 β’ 90
MobileNetV4_Conv Pretrained TFLite Models Collection These TFLite models were converted from the pretrained Pytorch weights on timm. β’ 7 items β’ Updated Jun 19, 2024 β’ 2
MobileNetV4 pretrained weights Collection Weights for MobileNet-V4 pretrained in timm β’ 17 items β’ Updated Sep 22, 2024 β’ 18
view article Article Training an Object Detection Model with AutoTrain By abhishek β’ Jun 5, 2024 β’ 14