GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Melady
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Melady
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Base model | Qwen/Qwen2.5-1.5B-Instruct |
| Architecture | Qwen2ForCausalLM with a multi-wavelet digit-embedding interface |
| Wavelets / scales | Haar, db4, Mexican Hat · scales 1, 2, 4 |
| Task | Context-aware time series forecasting |
| Language | English context + numeric digit tokens |
For a fixed-precision value such as -0.5000, each digit is rendered as an individual token:
text
-<|digit_0|>.<|digit_5|><|digit_0|><|digit_0|><|digit_0|>For each digit d in {0,...,9}, TempoWAVE:
d to d / 9 on a fixed grid;The ten digit codewords are verified to be distinct. Because Qwen ties its input and output embeddings by default, TempoWAVE separates them before freezing the input codebook, while the language-model head remains trainable so it can generate the new digit tokens.
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "Melady/TempoWAVE"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto") # Numeric values must be rendered as dedicated digit tokens, e.g. -0.5000 -># -<|digit_0|>.<|digit_5|><|digit_0|><|digit_0|><|digit_0|># See the GitHub repository for prompt formatting, generation, parsing, and# de-normalization helpers used to reproduce the paper's forecasts.For the full forecasting pipeline—prompt construction, fixed-precision generation, digit-token parsing, de-normalization, and MAE/RMSE evaluation—see the GitHub repository.
If you use TempoWAVE, please cite our paper:
bibtex
@inproceedings{cao2026tempowave, title = {Speaking Numbers to {LLM}s: Multi-Wavelet Number Embeddings for Time Series Forecasting}, author = {Cao, Defu and Lei, Zijie and Weng, Muyan and Sun, Jiao and Liu, Yan}, booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-ECAI)}, year = {2026}}from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "Melady/TempoWAVE"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto") # Numeric values must be rendered as dedicated digit tokens, e.g. -0.5000 -># -<|digit_0|>.<|digit_5|><|digit_0|><|digit_0|><|digit_0|># See the GitHub repository for prompt formatting, generation, parsing, and# de-normalization helpers used to reproduce the paper's forecasts.@inproceedings{cao2026tempowave, title = {Speaking Numbers to {LLM}s: Multi-Wavelet Number Embeddings for Time Series Forecasting}, author = {Cao, Defu and Lei, Zijie and Weng, Muyan and Sun, Jiao and Liu, Yan}, booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-ECAI)}, year = {2026}}