Team Ai
20 results

MoE

moenz /hf-9router2 likes8.5k downloads5m agoHugging Facemasterpieceexternal /gpt-oss-20b-moe-expert-power-traces-320k GPT-OSS-20B MoE Expert Power Traces (320k, ChipWhisperer) This dataset contains analog power traces captured with a ChipWhisperer Husky while running forced single-expert MoE computations derived from openai/gpt-oss-20b on an NVIDIA H100. What is recorded Each trace corresponds to one capture trial where: A fixed expert id is selected (expert_00 ... expert_31). A random hidden-state tensor is generated once per trial. The selected expert computation is executed… See the full description on the dataset page: https://huggingface.co/datasets/masterpieceexternal/gpt-oss-20b-moe-expert-power-traces-320k.audio-classification100K<n<1M0 likes3.3k downloads4mo agoHugging FacesunLry /moe-demo-clean RoboTwin MOE Demo Clean Raw RoboTwin demonstration data copied from bos:/lab-test/moe-demo-clean/. The dataset is organized by task directories such as place_can_basket-demo_clean-200/. Each task directory contains episode subdirectories with an HDF5 trajectory file and an instructions.json file. text1K<n<10K0 likes2.9k downloads4mo agoHugging FaceAvi2006 /spatial-moe-resultsimage10K<n<100K0 likes2.8k downloads8d agoHugging Facecore12345 /MoE_expert_selection_tracegated 📖 Introduction This repository serves as a supplement to our paper "Patterns behind Chaos: Forecasting Data Movement for Efficient Large-Scale MoE LLM Inference". It contains expert selection profiling traces of four top-tier MoE LLMs ranging from 235B to 1T (DeepSeek-R1, Kimi-K2-Thinking, Llama4-Marverick, and Qwen3-235B) across multiple benchmarks. For each query or request, we log the activated expert ID of every model layer of every generated token. We provide analyses and… See the full description on the dataset page: https://huggingface.co/datasets/core12345/MoE_expert_selection_trace.28 likes2.1k downloads5mo agoHugging FaceB4RryG /charlie-moe-nemotroncc-d004 Charlie MoE Nemotron-CC D004 Archive Dataset repository: B4RryG/charlie-moe-nemotroncc-d004. This repository preserves Nemotron-CC D004 inputs, data and resume indexes, native training checkpoints, and validation outputs. Each checkpoint and validation directory retains its own run or attempt identity so outputs from different weights are not combined. Repository layout Path Contents parquet/, metadata.json, and data manifests Nemotron-CC D004 input… See the full description on the dataset page: https://huggingface.co/datasets/B4RryG/charlie-moe-nemotroncc-d004.0 likes2k downloads4d agoHugging Face