Chronicle

A multimodal foundation model for joint language and time series understanding.

Chronicle is a compact 324M-parameter decoder-only transformer trained from scratch on natural language and time series within a single unified architecture. Text tokens and time-series patches share the same transformer blocks, attention mechanism, and residual stream — cross-modal capability emerges from shared parameters rather than from bolting a time-series encoder onto a pretrained LLM.

• 📄 Paper: Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding (Quinlan, Levasseur, Li, Zhu)
• 💻 Code & finetuning examples: github.com/InertialAI/Chronicle
• ☁️ Hosted API with self-serve finetuning (coming soon): inertialai.com

Checkpoints in this repo

Architecture

Usage

Weights ship as safetensors; model.py and tokenizer.py are a minimal, dependency-light inference implementation (torch, tiktoken). Verified example (text generation, CPU):

import json
import sys

import torch
from huggingface_hub import snapshot_download
from safetensors.torch import load_file

repo = snapshot_download("InertialAI/Chronicle")
sys.path.insert(0, repo)

from model import Chronicle, ChronicleConfig
from tokenizer import ChronicleTokenizer

config = ChronicleConfig(**json.load(open(f"{repo}/stage-2/config.json")))
model = Chronicle(config)
state = load_file(f"{repo}/stage-2/model.safetensors")
state = {k: v.float() if v.dtype is torch.bfloat16 else v for k, v in state.items()}
model.load_state_dict(state, strict=True)
model = model.float().eval()
model.cos, model.sin = model.cos.float(), model.sin.float()  # fp32 rotary on CPU

tokenizer = ChronicleTokenizer.from_directory(f"{repo}/tokenizer")
ids = [tokenizer.get_bos_token_id()] + tokenizer.encode("Time series forecasting is")
with torch.no_grad():
    for _ in range(16):
        out = model(torch.tensor([ids]))
        logits = out[0] if isinstance(out, tuple) else out
        ids.append(int(logits[0, -1].argmax()))
print(tokenizer.decode(ids[1:]))
# -> "Time series forecasting is a technique used to forecast future values
#     of a time series based on historical data."

For the time-series pathway (quantile forecasting via ts_patches) and forecast() / embed() conveniences, use the transformers-native port (in progress) or the hosted API (coming soon), which will serve these models. The finetuning recipes in the GitHub repo show the downstream-task protocols used in the paper.

Results

One backbone, evaluated against dedicated unimodal foundation models in both domains — the core claim is breadth: strong language understanding, state-of-the-art frozen time-series embeddings, and best-in-class multimodal forecasting, all from the same weights. Numbers below are from the paper.

Language understanding (19-task NLU average) — parity with text-only models of the same scale, trained on ~40× fewer text tokens:

Time series classification (24 UCR/UEA datasets, linear probe on frozen embeddings) — a new bar among TS foundation models:

Multimodal forecasting (Time-MMD, 9 domains, MAE ↓) — beats every supervised fusion baseline and every frozen FM-fusion pairing (baseline columns show the best baseline per metric):

Multimodal classification (TimeCAP: weather, finance, healthcare) — Chronicle-2 LoRA reaches 0.613 F1 / 0.757 AUC, ahead of every MM-TSFlib and FM-fusion baseline.

See the paper for full tables, protocols, and baselines, and the GitHub repo for reproduction scripts on public data.

Citation

@article{quinlan2026chronicle,
  title={Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding},
  author={Quinlan, Paul and Levasseur, Jeremy and Li, Qingguo and Zhu, Xiaodan},
  journal={arXiv preprint arXiv:2605.20268},
  year={2026}
}

License

Apache 2.0.