Instructions to use gabrielpondc/NL2SQL-StarCoder-15B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gabrielpondc/NL2SQL-StarCoder-15B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="gabrielpondc/NL2SQL-StarCoder-15B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gabrielpondc/NL2SQL-StarCoder-15B")
model = AutoModelForCausalLM.from_pretrained("gabrielpondc/NL2SQL-StarCoder-15B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gabrielpondc/NL2SQL-StarCoder-15B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gabrielpondc/NL2SQL-StarCoder-15B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gabrielpondc/NL2SQL-StarCoder-15B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gabrielpondc/NL2SQL-StarCoder-15B

SGLang

How to use gabrielpondc/NL2SQL-StarCoder-15B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "gabrielpondc/NL2SQL-StarCoder-15B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gabrielpondc/NL2SQL-StarCoder-15B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "gabrielpondc/NL2SQL-StarCoder-15B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gabrielpondc/NL2SQL-StarCoder-15B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gabrielpondc/NL2SQL-StarCoder-15B with Docker Model Runner:
```
docker model run hf.co/gabrielpondc/NL2SQL-StarCoder-15B
```

gabrielpondc commited on Apr 17, 2024

Commit

4ca645d

verified ·

1 Parent(s): 0db7324

Update README.md

Browse files

Files changed (1) hide show

README.md +24 -0

README.md CHANGED Viewed

@@ -43,6 +43,30 @@ CREATE TABLE "table_name" (
 """
 ```
 ## Quick Start
 ```python

 """
 ```
+But from test we recomended using the promt what sqlcoder was given:
+```
+### Instructions:
+Your task is to convert a question into a SQL query, given a Postgres database schema.
+Adhere to these rules:
+- **Deliberately go through the question and database schema word by word** to appropriately answer the question
+- **Use Table Aliases** to prevent ambiguity. For example, `SELECT table1.col1, table2.col1 FROM table1 JOIN table2 ON table1.id = table2.id`.
+- When creating a ratio, always cast the numerator as float
+### Input:
+Generate a SQL query that answers the question `{question}`.
+This query will run on a database whose schema is represented in this string:
+CREATE TABLE "table_name" (
+"col1" int,
+...
+...
+)
+### Response:
+Based on your instructions, here is the SQL query I have generated to answer the question `{question}`:
+```sql
+```
 ## Quick Start
 ```python