Instructions to use NumbersStation/nsql-llama-2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NumbersStation/nsql-llama-2-7B with Transformers:

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

pipe = pipeline("text-generation", model="NumbersStation/nsql-llama-2-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NumbersStation/nsql-llama-2-7B")
model = AutoModelForCausalLM.from_pretrained("NumbersStation/nsql-llama-2-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NumbersStation/nsql-llama-2-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NumbersStation/nsql-llama-2-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NumbersStation/nsql-llama-2-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NumbersStation/nsql-llama-2-7B

SGLang

How to use NumbersStation/nsql-llama-2-7B 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 "NumbersStation/nsql-llama-2-7B" \
    --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": "NumbersStation/nsql-llama-2-7B",
		"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 "NumbersStation/nsql-llama-2-7B" \
        --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": "NumbersStation/nsql-llama-2-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NumbersStation/nsql-llama-2-7B with Docker Model Runner:
```
docker model run hf.co/NumbersStation/nsql-llama-2-7B
```

vpm238 commited on Mar 10

Commit

c165371

verified ·

1 Parent(s): 4733274

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -41,7 +41,7 @@ NSQL-llama-2-7B was evaluated on the Spider benchmark, the standard academic eva
 | Model | Size | Execution Accuracy | Matching Accuracy |
 |-------|------|-------------------|-------------------|
-| **NSQL-llama-2-7B** | 7B | 75.0% | **66.3%** |
 | GPT-4 | ~1.8T | 76.2% | 41.9% |
 | GPT-3.5 Chat | — | 72.8% | 44.2% |
 | Llama-2-7B (base) | 7B | 29.1% | 19.3% |
@@ -63,7 +63,7 @@ NSQL-llama-2-7B was evaluated on the Spider benchmark, the standard academic eva
 2. **Matching Accuracy:** NSQL achieves 66.3% matching accuracy vs. GPT-4's 41.9% (+24.4 points), indicating more structurally correct SQL generation.
-3. **Efficiency:** NSQL achieves near-parity with GPT-4 on overall execution (75.0% vs 76.2%) while being ~250× smaller.
 4. **Local Deployment:** The 7B parameter size enables local deployment on commodity hardware, preserving data privacy.
@@ -92,7 +92,7 @@ On these complex query types, NSQL substantially outperforms GPT-4 while enablin
 | NSQL-350M | 350M | 51.7% | 45.6% |
 | NSQL-2B | 2B | 59.3% | 53.2% |
 | NSQL-6B | 6B | 63.6% | 57.4% |
-| **NSQL-llama-2-7B** | **7B** | **75.0%** | **66.3%** |
 ---

 | Model | Size | Execution Accuracy | Matching Accuracy |
 |-------|------|-------------------|-------------------|
+| **NSQL-llama-2-7B** | 7B | 78.1% | **66.3%** |
 | GPT-4 | ~1.8T | 76.2% | 41.9% |
 | GPT-3.5 Chat | — | 72.8% | 44.2% |
 | Llama-2-7B (base) | 7B | 29.1% | 19.3% |
 2. **Matching Accuracy:** NSQL achieves 66.3% matching accuracy vs. GPT-4's 41.9% (+24.4 points), indicating more structurally correct SQL generation.
+3. **Efficiency:** NSQL achieves near-parity with GPT-4 on overall execution (78.10% vs 76.2%) while being ~250× smaller.
 4. **Local Deployment:** The 7B parameter size enables local deployment on commodity hardware, preserving data privacy.
 | NSQL-350M | 350M | 51.7% | 45.6% |
 | NSQL-2B | 2B | 59.3% | 53.2% |
 | NSQL-6B | 6B | 63.6% | 57.4% |
+| **NSQL-llama-2-7B** | **7B** | **78.1%** | **66.3%** |
 ---