Instructions to use bugdaryan/WizardCoderSQL-15B-V1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bugdaryan/WizardCoderSQL-15B-V1.0 with Transformers:

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

pipe = pipeline("text-generation", model="bugdaryan/WizardCoderSQL-15B-V1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bugdaryan/WizardCoderSQL-15B-V1.0")
model = AutoModelForCausalLM.from_pretrained("bugdaryan/WizardCoderSQL-15B-V1.0")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bugdaryan/WizardCoderSQL-15B-V1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bugdaryan/WizardCoderSQL-15B-V1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bugdaryan/WizardCoderSQL-15B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bugdaryan/WizardCoderSQL-15B-V1.0

SGLang

How to use bugdaryan/WizardCoderSQL-15B-V1.0 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/WizardCoderSQL-15B-V1.0" \
    --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": "bugdaryan/WizardCoderSQL-15B-V1.0",
		"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 "bugdaryan/WizardCoderSQL-15B-V1.0" \
        --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": "bugdaryan/WizardCoderSQL-15B-V1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bugdaryan/WizardCoderSQL-15B-V1.0 with Docker Model Runner:
```
docker model run hf.co/bugdaryan/WizardCoderSQL-15B-V1.0
```

bugdaryan commited on Sep 15, 2023

Commit

85488c5

1 Parent(s): ff48091

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -6,6 +6,17 @@ language:
 - en
 tags:
 - cod
 ---
 # Wizard Coder SQL-Generation Model

 - en
 tags:
 - cod
+widget:
+- text: "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: Convert text to SQLite query: What is the song in the volume with the maximum weeks on top? CREATE TABLE volume (Song VARCHAR, Weeks_on_Top VARCHAR) ### Response:"
+  example_title: "Example 1"
+- text: "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: Convert text to SQLite query: Which Date has a Result of w 27–20? CREATE TABLE table_name_30 (date VARCHAR, result VARCHAR) ### Response:"
+  example_title: "Example 2"
+- text: "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: Convert text to SQLite query: Which party had Clair Engle as an incumbent? CREATE TABLE table_1342149_6 (party VARCHAR, incumbent VARCHAR) ### Response:"
+  example_title: "Example 3"
+- text: "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: Convert text to SQLite query: What is the 1994 when QF is 1999? CREATE TABLE table_name_4 (Id VARCHAR) ### Response:"
+  example_title: "Example 4"
+- text: "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction: Convert text to SQLite query: What date was the game held in Towson? CREATE TABLE table_name_76 (date VARCHAR, city VARCHAR) ### Response:"
+  example_title: "Example 5"
 ---
 # Wizard Coder SQL-Generation Model