support-pvelocity
commited on
Commit
•
0d9573b
1
Parent(s):
7bee052
Update README.md
Browse files
README.md
CHANGED
@@ -54,13 +54,13 @@ pipeline_tag: text-generation
|
|
54 |
|
55 |
## License
|
56 |
|
57 |
-
This model is governed by a custom commercial license from
|
58 |
|
59 |
## Intended Use
|
60 |
|
61 |
**Intended Use Cases**: This model is intended for commercial and research use in English. It is designed for text-to-SQL tasks, enabling users to generate SQL queries from natural language questions.
|
62 |
|
63 |
-
**Out-of-Scope Uses**: Any use that violates applicable laws or regulations, use in languages other than English, or any other use prohibited by the Acceptable Use Policy and Licensing Agreement for
|
64 |
|
65 |
## Model Capabilities
|
66 |
|
@@ -84,7 +84,7 @@ Llama-2-7B-instruct-text2sql is a powerful language model, but it may produce in
|
|
84 |
|
85 |
- **Training Libraries**: Custom training libraries
|
86 |
- **Training Hardware**: 1 A100 40GB GPU provided by Google Colab Pro+
|
87 |
-
- **Carbon Footprint**: Training all
|
88 |
|
89 |
## Training Data
|
90 |
|
|
|
54 |
|
55 |
## License
|
56 |
|
57 |
+
This model is governed by a custom commercial license from Llama. For details, please visit: [Custom Commercial License](https://ai.meta.com/resources/models-and-libraries/llama-downloads/)
|
58 |
|
59 |
## Intended Use
|
60 |
|
61 |
**Intended Use Cases**: This model is intended for commercial and research use in English. It is designed for text-to-SQL tasks, enabling users to generate SQL queries from natural language questions.
|
62 |
|
63 |
+
**Out-of-Scope Uses**: Any use that violates applicable laws or regulations, use in languages other than English, or any other use prohibited by the Acceptable Use Policy and Licensing Agreement for Llama and its variants.
|
64 |
|
65 |
## Model Capabilities
|
66 |
|
|
|
84 |
|
85 |
- **Training Libraries**: Custom training libraries
|
86 |
- **Training Hardware**: 1 A100 40GB GPU provided by Google Colab Pro+
|
87 |
+
- **Carbon Footprint**: Training all Llama models required 400K GPU hours on A100-80GB hardware with emissions offset by Meta's sustainability program.
|
88 |
|
89 |
## Training Data
|
90 |
|