Examples developed using GoMLX
๐ NEW ๐ KaLM-Gemma3 12B parameters: Tencent’s top-ranked sentence encoder for RAGs, using go-huggingface to load the model and tokenizer, and GoMLX to execute it.
๐ NEW ๐ Gemma 3 270M: Demonstrates ONNX-converted text generation (LLM) using the onnx-community/gemma-3-270m-it-ONNX model with GoMLX. It uses the
gomlx/onnx-gomlxpackage to convert the model, andgomlx/go-huggingfaceto download the model and run the tokenizer.๐ NEW ๐ GPT-2: Demonstrates text generation using the new (experimental) transformer and generator packages.
๐ NEW ๐ BERT-base-NER: A BERT-base model fine-tuned for Named Entity Recognition. It’s also an ONNX-converted model from the dslim/bert-base-NER model on HuggingFace.
๐ NEW ๐ MixedBread Reranker v1: A cross-encoder reranking example. See HuggingFace MixedBread Reranker v1 page. It uses the
gomlx/onnx-gomlxpackage to convert the model, andgomlx/go-huggingfaceto download the model and run the tokenizer.Diffusion model for Oxford Flowers 102 dataset (generates random flowers)
Flow Matching Study Notebook based on Meta’s “Flow Matching Guide and Code”.
Last, a trivial synthetic linear model, for those curious to see a barebones simple model.
Neural Style Transfer 10-year Celebration: see a demo written using GoMLX of the original paper.
Triplet Losses: various negative sampling strategies as well as various distance metrics.
AlphaZero AI for the game of Hive: It uses a trivial GNN to evaluate positions on the board. It includes a WASM demo (runs GoMLX in the browser!) and a command-line UI to test your skills!