Instructions to use fokyoum9/CodeLlama7B-Text2SQL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fokyoum9/CodeLlama7B-Text2SQL with Transformers:

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

pipe = pipeline("text-generation", model="fokyoum9/CodeLlama7B-Text2SQL")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fokyoum9/CodeLlama7B-Text2SQL")
model = AutoModelForCausalLM.from_pretrained("fokyoum9/CodeLlama7B-Text2SQL")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fokyoum9/CodeLlama7B-Text2SQL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fokyoum9/CodeLlama7B-Text2SQL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fokyoum9/CodeLlama7B-Text2SQL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fokyoum9/CodeLlama7B-Text2SQL

SGLang

How to use fokyoum9/CodeLlama7B-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 "fokyoum9/CodeLlama7B-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": "fokyoum9/CodeLlama7B-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 "fokyoum9/CodeLlama7B-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": "fokyoum9/CodeLlama7B-Text2SQL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fokyoum9/CodeLlama7B-Text2SQL with Docker Model Runner:
```
docker model run hf.co/fokyoum9/CodeLlama7B-Text2SQL
```

fokyoum9 commited on Dec 12, 2023

Commit

883b2bf

1 Parent(s): c3a39b2

Create README.md

Browse files

def make_inference(instruction):

prompt = f""" You are a powerful text-to-SQL model. Your job is to answer questions about a sqllite database only on the basis of the question's contents. You are given a question and context regarding one or
more tables. You must output the SQL query that answers the question
### question: {instruction}

### context:CREATE TABLE table_28281704_1 (country VARCHAR, city VARCHAR) # in the context , you should describe your schema, field

### answer:"""
inputs = tokenizer(prompt, return_tensors="pt", return_token_type_ids=False).to("cuda:0")

length = int(inputs.input_ids.size(1))
streamer=TextStreamer(tokenizer)

outputs = base_model.generate(**inputs,streamer=streamer, max_new_tokens=350,temperature=0.1, repetition_penalty=1.5, do_sample=False)
generated_text=tokenizer.decode(outputs[0], skip_special_tokens=True).replace("\n\n","")
return generated_text

Files changed (1) hide show

README.md +7 -0

README.md ADDED Viewed

	@@ -0,0 +1,7 @@

+---
+license: apache-2.0
+datasets:
+- b-mc2/sql-create-context
+language:
+- en
+---