Update README.md
Browse files
README.md
CHANGED
|
@@ -40,6 +40,14 @@ Drawing strength from the FinTalk-19k and Alpaca dataset, a curated collection f
|
|
| 40 |
- **Performance Optimisation:** Efficient performance across both CPU and GPU platforms.
|
| 41 |
- **Data Representation:** Utilises a combination of comprehensive Finance dataset, enabling content generation to professional standards.
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
## Model Usage
|
| 44 |
Experience the capabilities of the FinanceConnect model through a well-structured Python interface. To kick-start your exploration, follow the steps and snippets given below:
|
| 45 |
|
|
|
|
| 40 |
- **Performance Optimisation:** Efficient performance across both CPU and GPU platforms.
|
| 41 |
- **Data Representation:** Utilises a combination of comprehensive Finance dataset, enabling content generation to professional standards.
|
| 42 |
|
| 43 |
+
## Benchmarks
|
| 44 |
+
| **Benchmark** | **BloombergGPT 50B** | **FinanceConnect 13B** |
|
| 45 |
+
|--------------|--------------|--------------|
|
| 46 |
+
| MMLU | 39.8 | 51.43 |
|
| 47 |
+
| FPB | 51.1 | 57.2 |
|
| 48 |
+
| **Cost**| **$2.67 Million** | **$2.7x10^-5 Million** |
|
| 49 |
+
|
| 50 |
+
|
| 51 |
## Model Usage
|
| 52 |
Experience the capabilities of the FinanceConnect model through a well-structured Python interface. To kick-start your exploration, follow the steps and snippets given below:
|
| 53 |
|