readme updates
Browse files
README.md
CHANGED
|
@@ -4,7 +4,7 @@ tags:
|
|
| 4 |
- instruct
|
| 5 |
- finetune
|
| 6 |
model-index:
|
| 7 |
-
- name:
|
| 8 |
results: []
|
| 9 |
license: other
|
| 10 |
license_name: deepseek
|
|
@@ -15,14 +15,14 @@ datasets:
|
|
| 15 |
- cfahlgren1/natural-sql
|
| 16 |
---
|
| 17 |
|
| 18 |
-
# **
|
| 19 |
|
| 20 |
-
###
|
| 21 |
|
| 22 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/648a374f00f7a3374ee64b99/hafdsfrFCqrVbATIzV_EN.png" width="600">
|
| 23 |
|
| 24 |
-
**
|
| 25 |
-
|
| 26 |
|
| 27 |
Here is a write up, small test done [here](https://chatdb.ai/post/naturalsql-vs-sqlcoder-for-text-to-sql).
|
| 28 |
|
|
@@ -44,15 +44,15 @@ Here is a write up, small test done [here](https://chatdb.ai/post/naturalsql-vs-
|
|
| 44 |
|
| 45 |
## SQL-Eval on novel datasets not seen in training
|
| 46 |
|
| 47 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/648a374f00f7a3374ee64b99/
|
| 48 |
|
| 49 |
<em>Big thanks to the [defog](https://huggingface.co/defog) team for open sourcing [sql-eval](https://github.com/defog-ai/sql-eval)</em>👏
|
| 50 |
|
| 51 |
## SQL-Eval by SQL Category
|
| 52 |
|
| 53 |
-
**
|
| 54 |
|
| 55 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/648a374f00f7a3374ee64b99/
|
| 56 |
|
| 57 |
_The **date** category will be a strong focus in the next iteration of `v1`._
|
| 58 |
|
|
|
|
| 4 |
- instruct
|
| 5 |
- finetune
|
| 6 |
model-index:
|
| 7 |
+
- name: NaturalSQL-6.7B-v0.1
|
| 8 |
results: []
|
| 9 |
license: other
|
| 10 |
license_name: deepseek
|
|
|
|
| 15 |
- cfahlgren1/natural-sql
|
| 16 |
---
|
| 17 |
|
| 18 |
+
# **NaturalSQL-6.7B-v0.1**
|
| 19 |
|
| 20 |
+
### NaturalSQL is a series of models with state-of-the-art performance on Text to SQL instructions.
|
| 21 |
|
| 22 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/648a374f00f7a3374ee64b99/hafdsfrFCqrVbATIzV_EN.png" width="600">
|
| 23 |
|
| 24 |
+
**NaturalSQL** is a LLM that can translate natural language queries to SQL based on your schema. It is finetuned on 8k text to PostgreSQL Natural Language <> SQL pairs.
|
| 25 |
+
NaturalSQL matches the state of the art models in text to sql for it's size and produces the best in the field for complex questions.
|
| 26 |
|
| 27 |
Here is a write up, small test done [here](https://chatdb.ai/post/naturalsql-vs-sqlcoder-for-text-to-sql).
|
| 28 |
|
|
|
|
| 44 |
|
| 45 |
## SQL-Eval on novel datasets not seen in training
|
| 46 |
|
| 47 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/648a374f00f7a3374ee64b99/IZpVHJJzmapQ0gKV0Fb3q.png" width="800">
|
| 48 |
|
| 49 |
<em>Big thanks to the [defog](https://huggingface.co/defog) team for open sourcing [sql-eval](https://github.com/defog-ai/sql-eval)</em>👏
|
| 50 |
|
| 51 |
## SQL-Eval by SQL Category
|
| 52 |
|
| 53 |
+
**NaturalSQL-6.7B-v0 matches or outperforms other industry leading models in multiple categories!**
|
| 54 |
|
| 55 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/648a374f00f7a3374ee64b99/waXAf7crQQSqITp07BwEs.png" width="800">
|
| 56 |
|
| 57 |
_The **date** category will be a strong focus in the next iteration of `v1`._
|
| 58 |
|