Instructions to use bugdaryan/Code-Llama-2-13B-instruct-text2sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bugdaryan/Code-Llama-2-13B-instruct-text2sql with Transformers:

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

pipe = pipeline("text-generation", model="bugdaryan/Code-Llama-2-13B-instruct-text2sql")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bugdaryan/Code-Llama-2-13B-instruct-text2sql")
model = AutoModelForCausalLM.from_pretrained("bugdaryan/Code-Llama-2-13B-instruct-text2sql")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bugdaryan/Code-Llama-2-13B-instruct-text2sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bugdaryan/Code-Llama-2-13B-instruct-text2sql"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bugdaryan/Code-Llama-2-13B-instruct-text2sql",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bugdaryan/Code-Llama-2-13B-instruct-text2sql

SGLang

How to use bugdaryan/Code-Llama-2-13B-instruct-text2sql 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/Code-Llama-2-13B-instruct-text2sql" \
    --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/Code-Llama-2-13B-instruct-text2sql",
		"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/Code-Llama-2-13B-instruct-text2sql" \
        --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/Code-Llama-2-13B-instruct-text2sql",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bugdaryan/Code-Llama-2-13B-instruct-text2sql with Docker Model Runner:
```
docker model run hf.co/bugdaryan/Code-Llama-2-13B-instruct-text2sql
```

Context length supported and benchmarking with other models?

by Kshitizkhandelwal - opened Sep 19, 2023

Discussion

Kshitizkhandelwal

Sep 19, 2023

What is the context length supported for the model given that the schema can be relatively large? Also how does the model compare with other text to SQL models like gpt4/text-da-vinci 003?

bugdaryan

Owner Sep 20, 2023

Hello,

Thank you for your inquiry. Expanding context length support and conducting a detailed comparison and evaluation with models like gpt4/text-da-vinci-003 are both on our to-do list for the future. We appreciate your patience as we work on these improvements.

bugdaryan changed discussion status to closed Sep 20, 2023

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment