Views
No views yet
handler.py — Custom endpoint handler (loads model, serves predictions)Dockerfile — Custom container image (optional, for custom deployments)model/ — Symlink or copy of the Kronos model code from https://github.com/shiyu-coder/Kronosyour-username/kronos-gold-endpoint)model/ folder from Kronos:
1cp -r /path/to/Kronos/model ./
2git add . && git commit -m "Add Kronos handler" && git pushKRONOS_MODEL_ID=NeoQuasar/Kronos-baseKRONOS_TOKENIZER_ID=NeoQuasar/Kronos-Tokenizer-baseKRONOS_DEVICE=cudahttps://xxxxx.aws.endpoints.huggingface.cloud/NeoQuasar/Kronos-base.env file:1KRONOS_ENDPOINT_URL=https://xxxxx.aws.endpoints.huggingface.cloud/
2KRONOS_HF_TOKEN=hf_xxxxxxxxxxxx
3KRONOS_DEVICE=cpu # ignored when endpoint is setKRONOS_ENDPOINT_URL and KRONOS_HF_TOKEN are set, the bot will
use the remote GPU endpoint. Otherwise it falls back to local CPU (slow).1{
2 "inputs": {
3 "ohlcv": [[open, high, low, close, volume], ...],
4 "x_timestamps": ["2025-01-01T00:00:00", ...],
5 "y_timestamps": ["2025-01-01T16:00:00", ...],
6 "pred_len": 8,
7 "sample_count": 8,
8 "temperature": 1.0,
9 "top_p": 0.9
10 }
11}1{
2 "predictions": [
3 {"open": ..., "high": ..., "low": ..., "close": ..., "volume": ..., "amount": ...},
4 ...
5 ],
6 "timestamps": ["2025-01-01T16:00:00", ...],
7 "inference_seconds": 3.45
8}