Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,15 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
# Fine-Tuned Google T5 Model for Text to SQL Translation
|
| 6 |
|
| 7 |
-
|
| 8 |
|
| 9 |
## Model Details
|
| 10 |
|
|
@@ -14,16 +19,6 @@ This repository contains a fine-tuned version of the Google T5 model, specifical
|
|
| 14 |
- [sql-create-context Dataset](https://huggingface.co/datasets/b-mc2/sql-create-context)
|
| 15 |
- [Synthetic-Text-To-SQL Dataset](https://huggingface.co/datasets/gretelai/synthetic-text-to-sql)
|
| 16 |
|
| 17 |
-
## Fine-Tuning Datasets
|
| 18 |
-
|
| 19 |
-
1. **sql-create-context Dataset**:
|
| 20 |
-
- Created by modifying data from Seq2SQL and Spider datasets.
|
| 21 |
-
- [sql-create-context Dataset](https://huggingface.co/datasets/b-mc2/sql-create-context)
|
| 22 |
-
|
| 23 |
-
2. **Synthetic-Text-To-SQL Dataset**:
|
| 24 |
-
- A synthetic dataset for training language models to generate SQL queries from natural language prompts.
|
| 25 |
-
- [Synthetic-Text-To-SQL Dataset](https://huggingface.co/datasets/gretelai/synthetic-text-to-sql)
|
| 26 |
-
|
| 27 |
## Ongoing Work
|
| 28 |
|
| 29 |
Currently working to implement PICARD (Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models) to improve the results of this model. More details can be found in the original [PICARD paper](https://arxiv.org/abs/2109.05093).
|
|
@@ -42,4 +37,4 @@ Results are currently being evaluated and will be posted here soon.
|
|
| 42 |
- `tokenizer_config.json`: Tokenizer configuration settings.
|
| 43 |
- `model.safetensors`: Trained model weights.
|
| 44 |
- `generation_config.json`: Configuration for text generation.
|
| 45 |
-
- `config.json`: Model architecture configuration.
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- b-mc2/sql-create-context
|
| 5 |
+
- gretelai/synthetic_text_to_sql
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
---
|
| 9 |
|
| 10 |
# Fine-Tuned Google T5 Model for Text to SQL Translation
|
| 11 |
|
| 12 |
+
A fine-tuned version of the Google T5 model, trained for the task of translating natural language queries into SQL statements.
|
| 13 |
|
| 14 |
## Model Details
|
| 15 |
|
|
|
|
| 19 |
- [sql-create-context Dataset](https://huggingface.co/datasets/b-mc2/sql-create-context)
|
| 20 |
- [Synthetic-Text-To-SQL Dataset](https://huggingface.co/datasets/gretelai/synthetic-text-to-sql)
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
## Ongoing Work
|
| 23 |
|
| 24 |
Currently working to implement PICARD (Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models) to improve the results of this model. More details can be found in the original [PICARD paper](https://arxiv.org/abs/2109.05093).
|
|
|
|
| 37 |
- `tokenizer_config.json`: Tokenizer configuration settings.
|
| 38 |
- `model.safetensors`: Trained model weights.
|
| 39 |
- `generation_config.json`: Configuration for text generation.
|
| 40 |
+
- `config.json`: Model architecture configuration.
|