Update README.md
Browse files
README.md
CHANGED
|
@@ -11,8 +11,13 @@ tags:
|
|
| 11 |
---
|
| 12 |
|
| 13 |
|
|
|
|
| 14 |
|
| 15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
```python
|
| 17 |
# Use a pipeline as a high-level helper
|
| 18 |
from transformers import pipeline
|
|
@@ -37,4 +42,16 @@ outputs = pipe_msg(
|
|
| 37 |
max_new_tokens=256,
|
| 38 |
)
|
| 39 |
print(outputs[0]["generated_text"][-1])
|
| 40 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
|
| 14 |
+
# text2sql-8b-instruct-v1
|
| 15 |
|
| 16 |
+
## Summary
|
| 17 |
+
it is a natural language-to-SQL conversion model optimized specifically for Chinese and English users. It is based on the llama-3-chinese-8b-instruct-v3 model. We used the latest optimization algorithms to improve the performance of the model, especially in handling complex queries and multi-table joins.
|
| 18 |
+
|
| 19 |
+
## Usage:
|
| 20 |
+
Please upgrade the `transformers` package to ensure it supports Llama3 models. The current version we are using is `4.41.2`.
|
| 21 |
```python
|
| 22 |
# Use a pipeline as a high-level helper
|
| 23 |
from transformers import pipeline
|
|
|
|
| 42 |
max_new_tokens=256,
|
| 43 |
)
|
| 44 |
print(outputs[0]["generated_text"][-1])
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
## Ethical Considerations
|
| 49 |
+
|
| 50 |
+
While fine-tuned for text to sql, this model inherits the ethical considerations of the base Llama 3 model. Use responsibly and implement additional safeguards as needed for your application.
|
| 51 |
+
|
| 52 |
+
## Availability
|
| 53 |
+
|
| 54 |
+
The model is available through:
|
| 55 |
+
- [Hugging Face](https://huggingface.co/xbrain/text2sql-8b-instruct-v1)
|
| 56 |
+
|
| 57 |
+
For full details on responsible use, ethical considerations, and latest benchmarks, please refer to the [official Llama 3 documentation](https://llama.meta.com/).
|