datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
wsinfer-model-zoo-jsonThis is the registry of models in the WSInfer Model Zoo.
See https://wsinfer.readthedocs.io/en/latest/ and https://github.com/SBU-BMI/wsinfer-zoo for more information.
awq-model-zooGelGenie-Model-ZooThis is the registry of models which can be used both in PyTorch (standalone) or in the GelGenie QuPath Extension. You can access the individual models from the links provided.
For more details, please visit our open-source codebase here: https://github.com/mattaq31/GelGenie.
ModelZooawq-model-zoo
yujiepan/awq-model-zoo
Here are some pre-computed awq information (scales & clips) used in llm-awq.
Scripts
Install the forked llm-awq at https://github.com/yujiepan-work/llm-awq/tree/a41a08e79d8eb3d6335485b3625410af22a74426. Note: works with transformers==4.35.2
Generating awq-info.pt:
python do_awq.py --model_id mistralai/Mistral-7B-v0.1 --w_bit 8 --q_group_size 128 --dump_awq ./awq-info.pt
Load a quantized model: You can use the offical repo to get a fake/real… See the full description on the dataset page: https://huggingface.co/datasets/yujiepan/awq-model-zoo.Model_zoosupermix-model-zoo
Supermix Model Zoo
Updated: 2026-08-12T01:47:36.936800Z
Model count: 36
Total size: 3.04 GiB
Owner: Kai9987kai
Integrity
Every ZIP is content-bound in manifest.json by exact byte size and SHA-256. Supermix Studio verifies both plus safe ZIP structure before atomically installing an artifact.
Cognitive Leap additions
supermix_cognitive_leap_v50_chat_20260812.zip: legacy chat checkpoint archive; manual selection only.… See the full description on the dataset page: https://huggingface.co/datasets/Kai9987kai/supermix-model-zoo.MoE-Transformer-Model-Zoos
MoE Transformer Model Zoos
The MoE Transformer Model Zoos consist of two datasets: AGNews-MoEs and MNIST-MoEs. These datasets contain small-scale Mixture-of-Experts (MoE) Transformer weights and are designed to support research on metanetworks for predicting model generalization directly from internal weight structures.
Folder Structure
The dataset is provided as a data.zip file. After extraction, the directory structure is organized as follows:
data/
├── ag_news/
│ ├──… See the full description on the dataset page: https://huggingface.co/datasets/JohnDoe4765/MoE-Transformer-Model-Zoos.edgedeploy-modelzoowsinsight-model-zoo-json