Text Classification
ONNX
PyTorch
English
multilingual
pico-type
byte-level
content-classification
multi-head
classifier
edge-ai
mobile
ios
android
webassembly
wasm
browser
code-detection
language-detection
programming-language
natural-language
clipboard
mcp
model-context-protocol
tiny
lightweight
small-model
onnx-runtime
real-time
inference
matryoshka
adaptive-compute
no-tokenizer
byte-embedding
multi-task
multi-label
risk-detection
secret-detection
mime-type
file-type
modality
edge-computing
serverless
cloudflare-workers
pico
transformer
attention
conv1d
rope
open-source
apache-2
production-ready
zero-dependency
Eval Results (legacy)
| { | |
| "tiers": [ | |
| "tiny", | |
| "small", | |
| "base", | |
| "pro" | |
| ], | |
| "tier_dims": { | |
| "tiny": 16, | |
| "small": 64, | |
| "base": 192, | |
| "pro": 576 | |
| }, | |
| "params": { | |
| "tiny": 1434344, | |
| "small": 1445480, | |
| "base": 1475176, | |
| "pro": 1564264 | |
| }, | |
| "head_classes": { | |
| "coarse": 12, | |
| "modality": 8, | |
| "subtype": 24, | |
| "code_lang": 62, | |
| "text_lang": 30, | |
| "file_mime": 90, | |
| "risk": 6 | |
| }, | |
| "max_bytes": 1024, | |
| "opset": 18 | |
| } |