Kronos Mini — VN30 SFT

Predictor fine-tuned on the fixed VNDIRECT VN30 snapshot, on the PC rerun. Selected by native validation including epoch zero: epoch 5, training seed 42. This is exploratory research. Provider OHLC construction is not fully verified. No claim of superiority to Naive or of deployable trading performance is made.

Load

Use the pinned Kronos implementation 67b630e67f6a18c9e9be918d9b4337c960db1e9a and Kronos.from_pretrained(local_model_directory). Tokenizer: NeoQuasar/Kronos-Tokenizer-2k at 26966d0035065a0cae0ebad7af8ece35bc1fb51c. The custom Kronos architecture does not automatically provide a hosted inference API. The project includes a local React/FastAPI dashboard; no Space is required.

Protocol and provenance

128 historical sessions, 20 future sessions, FP32, mean of 3 paths, temperature 1.0, top-p 0.9. The tokenizer is frozen during fine-tuning. Missing volume/amount are zero-filled by the adapter. Snapshot SHA256: fee0bd8c240a9d2be4ef5c9d287eede6c5506b0358c25545e72de99709da4fd2. See provenance.json and inference_spec.json for revision and byte hashes. No raw dataset, optimizer, RNG snapshots or credentials are included.

License

MIT, retaining the original Kronos attribution. See LICENSE.

Downloads last month: -

Safetensors

Model size

4.11M params

Tensor type

F32

Inference Providers NEW

Time Series Forecasting

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for neikhn/kronos-mini-vn30-sft

Base model

NeoQuasar/Kronos-mini

Finetuned

(2)

this model