wetron

A browser-native inspector for neural network model files that opens a model and explores its computation graph, metadata, tensor shapes and weight statistics with no upload and no server.

Visit website sultaniman.github.io

wetron is a browser-native inspector for neural network models and GGUF LLM files. It opens a model file and shows its computation graph, metadata, tensor shapes and weight statistics entirely client-side, so a proprietary, medical or otherwise sensitive model never has to be uploaded to a hosted service.

It parses ONNX, TFLite, Keras, GGUF, TorchScript, ExecuTorch and TensorFlow SavedModel files using browser APIs together with libraries such as protobufjs and flatbuffers, decoding weight bytes lazily only when a property panel needs them. It ships as a set of embeddable packages, including separate React and Svelte views, so other open-source projects such as model registries can embed it directly.

More in Models

See all 405

mini-AGI
github.com
A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.
- Models
Applied Inference Lab: Compliance Control Embedding Stack
github.com
An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.
- Models
- Security
peekaboolean
github.com
A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.
- Models
- Inference

More in Models

mini-AGI

Applied Inference Lab: Compliance Control Embedding Stack

peekaboolean

Cookies