Instructions to use defog/llama-3-sqlcoder-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use defog/llama-3-sqlcoder-8b with Transformers:

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

pipe = pipeline("text-generation", model="defog/llama-3-sqlcoder-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("defog/llama-3-sqlcoder-8b")
model = AutoModelForCausalLM.from_pretrained("defog/llama-3-sqlcoder-8b")
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
Local Apps Settings

vLLM

How to use defog/llama-3-sqlcoder-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "defog/llama-3-sqlcoder-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "defog/llama-3-sqlcoder-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/defog/llama-3-sqlcoder-8b

SGLang

How to use defog/llama-3-sqlcoder-8b 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 "defog/llama-3-sqlcoder-8b" \
    --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": "defog/llama-3-sqlcoder-8b",
		"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 "defog/llama-3-sqlcoder-8b" \
        --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": "defog/llama-3-sqlcoder-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use defog/llama-3-sqlcoder-8b with Docker Model Runner:
```
docker model run hf.co/defog/llama-3-sqlcoder-8b
```

Unable to import to Bedrock

#22

by kalkarprashant - opened Oct 28, 2024

Discussion

kalkarprashant

Oct 28, 2024

Followed following steps to import to sagemaker:

Import the model to s3.

git lfs install
git clone --depth=1 --progress https://huggingface.co/defog/llama-3-sqlcoder-8b
tar zcvf model.tar.gz *
aws s3 cp model.tar.gz s3://.../llama-3-sqlcoder-8b/model.tar.gz

Used the script provided for the SageMaker deployment to deploy to sageMaker along with model_data set to s3.
The deployment to sagemaker works fine but was not able to get it to import for Bedrock.

When importing to bedrock I am getting following error:

Amazon bedrock could not find the expected file s3://.../config.json. Make sure the model is in Huggingface format and that the file exists

The file does exists as its already there in the repo (taken during get clone). I am assuming the format is also hugging face one.

Any help will be great in this regards
Prashant

wongjingping

Oct 29, 2024

Hi @kalkarprashant ,

We do have the config.json in our repository here: https://huggingface.co/defog/llama-3-sqlcoder-8b/blob/main/config.json , hence it seems like the issue is with how you're using the inference engine, which unfortunately we do not support.

My guess is that the file might have been missed out somehow during the intermediate steps while uploading it, and my recommendation would be to start over with the same steps.

wongjingping changed discussion status to closed Oct 29, 2024

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