Update README.md
Browse files
README.md
CHANGED
|
@@ -9,8 +9,32 @@ tags:
|
|
| 9 |
license: apache-2.0
|
| 10 |
language:
|
| 11 |
- en
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
# Uploaded model
|
| 15 |
|
| 16 |
- **Developed by:** imahwashere
|
|
@@ -19,4 +43,4 @@ language:
|
|
| 19 |
|
| 20 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 21 |
|
| 22 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 9 |
license: apache-2.0
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
+
datasets:
|
| 13 |
+
- gretelai/synthetic_text_to_sql
|
| 14 |
---
|
| 15 |
|
| 16 |
+
### Text-to-SQL Model
|
| 17 |
+
A fine-tuned Llama 3.2 3B model specialized for converting natural language queries into SQL statements. This model transforms everyday questions into precise database queries, making data accessible to everyone.
|
| 18 |
+
|
| 19 |
+
### Desired Use Cases
|
| 20 |
+
Perfect for applications requiring natural language to SQL conversion:
|
| 21 |
+
|
| 22 |
+
Business Intelligence: "Show me sales by region for last quarter"
|
| 23 |
+
Data Analytics: "Find customers who haven't purchased in 6 months"
|
| 24 |
+
Reporting: "What are the top 10 products by revenue?"
|
| 25 |
+
Database Querying: Making databases accessible to non-technical users
|
| 26 |
+
|
| 27 |
+
### Training Data
|
| 28 |
+
Trained on the gretelai/synthetic_text_to_sql dataset, which provides:
|
| 29 |
+
|
| 30 |
+
High-quality synthetic text-to-SQL pairs
|
| 31 |
+
Diverse query patterns and complexity levels
|
| 32 |
+
Multiple database schemas and domains
|
| 33 |
+
Robust coverage of SQL operations and functions
|
| 34 |
+
|
| 35 |
+
### Model Performance
|
| 36 |
+
IDK MAN, it does what it does brev.
|
| 37 |
+
|
| 38 |
# Uploaded model
|
| 39 |
|
| 40 |
- **Developed by:** imahwashere
|
|
|
|
| 43 |
|
| 44 |
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
| 45 |
|
| 46 |
+
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|