bol20162021
commited on
Commit
•
b6a8eb3
1
Parent(s):
1a06498
Update README.md
Browse files
README.md
CHANGED
@@ -6,13 +6,13 @@ datasets:
|
|
6 |
language:
|
7 |
- en
|
8 |
---
|
9 |
-
#
|
10 |
|
11 |
## Model Description
|
12 |
|
13 |
NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks.
|
14 |
|
15 |
-
In this repository we are introducing a new member of NSQL,
|
16 |
|
17 |
Use of this model is governed by the Meta’s Llama 2 Community License Agreement. Please review and accept the license before downloading the model weights and tokenizer
|
18 |
|
@@ -69,8 +69,8 @@ The model was designed for text-to-SQL generation tasks from given table schema
|
|
69 |
```python
|
70 |
import torch
|
71 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
72 |
-
tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/
|
73 |
-
model = AutoModelForCausalLM.from_pretrained("sambanovasystems/
|
74 |
text = "CREATE TABLE stadium (
|
75 |
stadium_id number,
|
76 |
location text,
|
|
|
6 |
language:
|
7 |
- en
|
8 |
---
|
9 |
+
# SambaCoder-nsql-llama-2-70b
|
10 |
|
11 |
## Model Description
|
12 |
|
13 |
NSQL is a family of autoregressive open-source large foundation models (FMs) designed specifically for SQL generation tasks.
|
14 |
|
15 |
+
In this repository we are introducing a new member of NSQL, SambaCoder-nsql-llama-2-70b. It's based on Meta's original [Llama-2 70B model](https://huggingface.co/meta-llama/Llama-2-70b) and further pre-trained on a dataset of general SQL queries and then fine-tuned on a dataset composed of text-to-SQL pairs.
|
16 |
|
17 |
Use of this model is governed by the Meta’s Llama 2 Community License Agreement. Please review and accept the license before downloading the model weights and tokenizer
|
18 |
|
|
|
69 |
```python
|
70 |
import torch
|
71 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
72 |
+
tokenizer = AutoTokenizer.from_pretrained("sambanovasystems/SambaCoder-nsql-llama-2-70b")
|
73 |
+
model = AutoModelForCausalLM.from_pretrained("sambanovasystems/SambaCoder-nsql-llama-2-70b", torch_dtype=torch.bfloat16)
|
74 |
text = "CREATE TABLE stadium (
|
75 |
stadium_id number,
|
76 |
location text,
|