Update README.md
Browse files
README.md
CHANGED
|
@@ -95,6 +95,10 @@ The below model scripts can be used for any of the above TTM models. Please upda
|
|
| 95 |
|
| 96 |
## Benchmarks
|
| 97 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
TTM outperforms popular benchmarks such as TimesFM, Moirai, Chronos, Lag-Llama, Moment, GPT4TS, TimeLLM, LLMTime in zero/fewshot forecasting while reducing computational requirements significantly.
|
| 99 |
Moreover, TTMs are lightweight and can be executed even on CPU-only machines, enhancing usability and fostering wider
|
| 100 |
adoption in resource-constrained environments. For more details, refer to our [paper](https://arxiv.org/pdf/2401.03955.pdf).
|
|
|
|
| 95 |
|
| 96 |
## Benchmarks
|
| 97 |
|
| 98 |
+
<p align="center" width="100%">
|
| 99 |
+
<img src="benchmarks.webp" width="300">
|
| 100 |
+
</p>
|
| 101 |
+
|
| 102 |
TTM outperforms popular benchmarks such as TimesFM, Moirai, Chronos, Lag-Llama, Moment, GPT4TS, TimeLLM, LLMTime in zero/fewshot forecasting while reducing computational requirements significantly.
|
| 103 |
Moreover, TTMs are lightweight and can be executed even on CPU-only machines, enhancing usability and fostering wider
|
| 104 |
adoption in resource-constrained environments. For more details, refer to our [paper](https://arxiv.org/pdf/2401.03955.pdf).
|