Instructions to use ansumanpandey/codgen-finetuned-SQLQueryGeneration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ansumanpandey/codgen-finetuned-SQLQueryGeneration with Transformers:

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

pipe = pipeline("text-generation", model="ansumanpandey/codgen-finetuned-SQLQueryGeneration")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ansumanpandey/codgen-finetuned-SQLQueryGeneration")
model = AutoModelForCausalLM.from_pretrained("ansumanpandey/codgen-finetuned-SQLQueryGeneration")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ansumanpandey/codgen-finetuned-SQLQueryGeneration with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ansumanpandey/codgen-finetuned-SQLQueryGeneration

SGLang

How to use ansumanpandey/codgen-finetuned-SQLQueryGeneration 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 "ansumanpandey/codgen-finetuned-SQLQueryGeneration" \
    --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": "ansumanpandey/codgen-finetuned-SQLQueryGeneration",
		"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 "ansumanpandey/codgen-finetuned-SQLQueryGeneration" \
        --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": "ansumanpandey/codgen-finetuned-SQLQueryGeneration",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ansumanpandey/codgen-finetuned-SQLQueryGeneration with Docker Model Runner:
```
docker model run hf.co/ansumanpandey/codgen-finetuned-SQLQueryGeneration
```

ansumanpandey commited on Apr 5, 2024

Commit

b44bdcb

verified ·

1 Parent(s): bdb0145

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -16

README.md CHANGED Viewed

@@ -30,20 +30,6 @@ This model is intended for the automatic generation of SQL queries from descript
 This model can be used with the Hugging Face Transformers library. Here is a quick example:
 ***************************
-from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("ansumanpandey/codgen-finetuned-SQLQueryGeneration")
-model = AutoModelForCausalLM.from_pretrained("ansumanpandey/codgen-finetuned-SQLQueryGeneration")
-def get_sql(query):
-  input_text = "Write a SQL query to %s </s>" % query
-  features = tokenizer([input_text], return_tensors='pt')
-  output = model.generate(input_ids=features['input_ids'],
-               attention_mask=features['attention_mask'],
-               max_new_tokens=70)
-  sql_query= tokenizer.decode(output[0])
-  return sql_query
 ***************************

 This model can be used with the Hugging Face Transformers library. Here is a quick example:
 ***************************
+The link:
+https://huggingface.co/ansumanpandey/codgen-finetuned-SQLQueryGeneration/blob/main/The%20SQL%20Generation%20Code
 ***************************