Instructions to use kristiannordby/llama3-sqlcoder-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kristiannordby/llama3-sqlcoder-ft with Transformers:

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

pipe = pipeline("text-generation", model="kristiannordby/llama3-sqlcoder-ft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kristiannordby/llama3-sqlcoder-ft")
model = AutoModelForCausalLM.from_pretrained("kristiannordby/llama3-sqlcoder-ft")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kristiannordby/llama3-sqlcoder-ft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kristiannordby/llama3-sqlcoder-ft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kristiannordby/llama3-sqlcoder-ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kristiannordby/llama3-sqlcoder-ft

SGLang

How to use kristiannordby/llama3-sqlcoder-ft 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 "kristiannordby/llama3-sqlcoder-ft" \
    --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": "kristiannordby/llama3-sqlcoder-ft",
		"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 "kristiannordby/llama3-sqlcoder-ft" \
        --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": "kristiannordby/llama3-sqlcoder-ft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kristiannordby/llama3-sqlcoder-ft with Docker Model Runner:
```
docker model run hf.co/kristiannordby/llama3-sqlcoder-ft
```

kristiannordby commited on Jun 2, 2025

Commit

5343822

verified ·

1 Parent(s): 9cf3c6e

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -4

README.md CHANGED Viewed

@@ -58,10 +58,15 @@ def build_output(sql):
     return f"{sql.strip()}\n"
 create_table_statements = "YOUR TABLE SCHEMA HERE"
-inputs = build_prompt("YOUR PROMPT HERE", create_table_statements)
-input_ids = tokenizer(inputs, return_tensors="pt", padding = True, truncation = True, max_length = 512).input_ids.to(model.device)
-outputs = model.generate(input_ids, max_new_tokens=100)
-output = tokenizer.decode(outputs[0])
 ```

     return f"{sql.strip()}\n"
 create_table_statements = "YOUR TABLE SCHEMA HERE"
+def sqllamma(question):
+    input_ids = tokenizer(build_prompt(question, create_table_statements), return_tensors="pt", padding = True, truncation = True, max_length = 512).input_ids.to(model.device)
+    outputs = model.generate(input_ids, max_new_tokens=100)
+    output = tokenizer.decode(outputs[0])
+    sql = output.split("###")[3].split("[SQL]")[1].strip()
+    return sql
+sqllama("YOUR QUESTION HERE")
 ```