Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,102 @@
+---
+license: apache-2.0
+tags:
+  - time-series
+  - forecasting
+  - chronos
+  - patch-aliasing
+language:
+  - en
+---
+
+# Chronos-Bolt Patch Sweep
+
+A collection of **Chronos-Bolt Tiny** models retrained **from scratch** (random weights) on the official [Chronos pre-training corpus](https://huggingface.co/datasets/autogluon/chronos_datasets) (TSMixup 10M + KernelSynth 1M), varying only the **patch geometry** (input_patch_size `P` and input_patch_stride `S`).
+
+The goal is to study **structural aliasing** in patched time-series transformers: how the choice of patch size and stride affects the model's ability to represent different frequency components.
+
+## Models
+
+| Subfolder | P | S | Overlap Ratio | Approx Patches | Params | Final Loss | Speed (it/s) |
+|-----------|---|---|---------------|-----------------|--------|------------|--------------|
+| `p16-s16-seed42` | 16 | 16 | 0.00 (contiguous) | 128 | 8.65M | 36.09 | 4.94 |
+| `p16-s12-seed42` | 16 | 12 | 0.25 | 170 | 8.65M | 35.34 | 6.78 |
+| `p16-s8-seed42` | 16 | 8 | 0.50 | 255 | 8.65M | 36.97 | 3.80 |
+| `p16-s4-seed42` | 16 | 4 | 0.75 | 509 | 8.65M | 36.70 | 3.58 |
+| `p8-s8-seed42` | 8 | 8 | 0.00 (contiguous) | 256 | 8.63M | 37.62 | 7.03 |
+| `p24-s24-seed42` | 24 | 24 | 0.00 (contiguous) | 86 | 8.67M | 34.90 | 4.50 |
+
+### Experimental design
+
+- **Overlap axis** (fixed P=16, varying S): `S=16` (no overlap) → `S=12` (25%) → `S=8` (50%) → `S=4` (75%). Tests whether overlapping patches reduce aliasing artifacts.
+- **Patch-size axis** (contiguous, S=P): `P=8` → `P=16` → `P=24`. Tests how the patch size itself (the effective sampling window) affects frequency representation.
+
+All other hyperparameters are fixed at the official Chronos-Bolt Tiny values so any downstream difference is attributable to P/S alone.
+
+## Training details
+
+- **Base architecture**: [amazon/chronos-bolt-tiny](https://huggingface.co/amazon/chronos-bolt-tiny) (T5-based, ~8.65M params)
+- **Weights**: trained from scratch (random init), NOT fine-tuned from the official checkpoint
+- **Dataset**: `autogluon/chronos_datasets` — TSMixup 10M + KernelSynth 1M (official Chronos corpus)
+- **Steps**: 10,000 (vs official 200k — reduced compute budget; all models compared only against each other)
+- **Batch size**: 32
+- **Optimizer**: AdamW (fused), LR=1e-3, linear decay, no warmup
+- **Precision**: fp32 + TF32 matmuls on NVIDIA RTX 5060 Laptop GPU
+- **Context length**: 2048 tokens
+- **Prediction length**: 64 steps
+- **Quantiles**: 9 (0.1 to 0.9)
+
+## Usage
+
+```python
+from chronos import ChronosBoltPipeline
+import torch
+
+# Load any single model
+pipeline = ChronosBoltPipeline.from_pretrained(
+    "federicosabbadini/chronos-bolt-patch-sweep",
+    subfolder="p16-s16-seed42",
+    device_map="cuda",
+    torch_dtype=torch.float32,
+)
+
+# Forecast
+context = torch.tensor([...])  # your time series as a 1D tensor
+forecast = pipeline.predict(context, prediction_length=64)
+# forecast shape: (1, num_samples, 64)
+```
+
+### Load all models for comparison
+
+```python
+from chronos import ChronosBoltPipeline
+import torch
+
+REPO = "federicosabbadini/chronos-bolt-patch-sweep"
+MODEL_NAMES = [
+    "p16-s16-seed42", "p16-s12-seed42", "p16-s8-seed42",
+    "p16-s4-seed42", "p8-s8-seed42", "p24-s24-seed42",
+]
+
+models = {}
+for name in MODEL_NAMES:
+    models[name] = ChronosBoltPipeline.from_pretrained(
+        REPO, subfolder=name,
+        device_map="cuda", torch_dtype=torch.float32,
+    )
+```
+
+## Files per model
+
+Each subfolder contains:
+- `config.json` — HuggingFace model config (includes `chronos_config` with P, S values)
+- `model.safetensors` — trained weights (~33 MB)
+- `run_config.json` — full provenance + training result metadata
+- `loss_history.npy` — per-step training loss array (10,000 values)
+- `loss_curve.png` — training loss plot
+
+The root `manifest.csv` summarizes all finished runs.
+
+## Citation
+
+This work is part of a research project on patch aliasing in time-series transformers. The base model architecture and training pipeline are adapted from [Chronos](https://github.com/amazon-science/chronos-forecasting) (Apache-2.0).