wasmicro
Tiny transformer inference for the web. One file. No build step.
WASM module
| Status | loading… |
|---|---|
| Version | — |
| Bundle size | — |
| Cold load time | — |
Matmul benchmark
Runs n × n matrix multiplication inside WASM.
(click Run)
Load model — WasmPipeline
Supports BERT (embeddings), GPT-2 and
T5 (generation). Model type is auto-detected from
config.json — no hardcoded parameters needed.
model.safetensors |
|
|---|---|
vocab.txt (BERT)vocab.json (GPT-2/T5) |
|
config.json (required) |
|
merges.txt (GPT-2/T5 only) |
(no model loaded)
Semantic search BERT
(load a BERT model to enable)
Text generation
(load a GPT-2 or T5 model to enable)
T5 tip: prefix your prompt with a task instruction, e.g. "translate English to French: Hello" or "summarize: The quick brown fox…"