Instructions to use bugdaryan/MistralSQL-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bugdaryan/MistralSQL-7b with Transformers:

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

pipe = pipeline("text-generation", model="bugdaryan/MistralSQL-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bugdaryan/MistralSQL-7b")
model = AutoModelForCausalLM.from_pretrained("bugdaryan/MistralSQL-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bugdaryan/MistralSQL-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bugdaryan/MistralSQL-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bugdaryan/MistralSQL-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bugdaryan/MistralSQL-7b

SGLang

How to use bugdaryan/MistralSQL-7b 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 "bugdaryan/MistralSQL-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bugdaryan/MistralSQL-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "bugdaryan/MistralSQL-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bugdaryan/MistralSQL-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bugdaryan/MistralSQL-7b with Docker Model Runner:
```
docker model run hf.co/bugdaryan/MistralSQL-7b
```

bugdaryan commited on Oct 8, 2023

Commit

1542840

1 Parent(s): f1eba2b

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -7,6 +7,17 @@ language:
 library_name: peft
 tags:
 - text2sql
 ---
 # Model Card for MistralSQL-7B

 library_name: peft
 tags:
 - text2sql
+widget:
+- text: "[INST] Write SQLite query to answer the following question given the database schema. Please wrap your code answer using ```: Schema: CREATE TABLE head (age INTEGER) Question: How many heads of the departments are older than 56 ? [/INST] Here is the SQLite query to answer to the question: How many heads of the departments are older than 56 ?: ```"
+  example_title: "Example 1"
+- text: "[INST] Write SQLite query to answer the following question given the database schema. Please wrap your code answer using ```: Schema: CREATE TABLE people (first_name VARCHAR) Question: List the first names of people in alphabetical order? [/INST] Here is the SQLite query to answer to the question: List the first names of people in alphabetical order?: ```"
+  example_title: "Example 2"
+- text: "[INST] Write SQLite query to answer the following question given the database schema. Please wrap your code answer using ```: Schema: CREATE TABLE weather (zip_code VARCHAR, mean_sea_level_pressure_inches INTEGER) Question: What is the zip code in which the average mean sea level pressure is the lowest? [/INST] Here is the SQLite query to answer to the question: What is the zip code in which the average mean sea level pressure is the lowest?: ```"
+  example_title: "Example 3"
+- text: "[INST] Write SQLite query to answer the following question given the database schema. Please wrap your code answer using ```: Schema: CREATE TABLE weather (date VARCHAR, mean_temperature_f VARCHAR, mean_humidity VARCHAR, max_gust_speed_mph VARCHAR) Question: What are the date, mean temperature and mean humidity for the top 3 days with the largest max gust speeds? [/INST] Here is the SQLite query to answer to the question: What are the date, mean temperature and mean humidity for the top 3 days with the largest max gust speeds?: ```"
+  example_title: "Example 4"
+- text: "[INST] Write SQLite query to answer the following question given the database schema. Please wrap your code answer using ```: Schema: CREATE TABLE trip (end_station_id VARCHAR); CREATE TABLE station (id VARCHAR, city VARCHAR) Question: Count the number of trips that did not end in San Francisco city. [/INST] Here is the SQLite query to answer to the question: Count the number of trips that did not end in San Francisco city.: ```"
+  example_title: "Example 5"
 ---
 # Model Card for MistralSQL-7B