Instructions to use inference-net/Schematron-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inference-net/Schematron-3B with Transformers:

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

pipe = pipeline("text-generation", model="inference-net/Schematron-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("inference-net/Schematron-3B")
model = AutoModelForCausalLM.from_pretrained("inference-net/Schematron-3B")
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
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use inference-net/Schematron-3B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/inference-net/Schematron-3B

SGLang

How to use inference-net/Schematron-3B 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 "inference-net/Schematron-3B" \
    --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": "inference-net/Schematron-3B",
		"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 "inference-net/Schematron-3B" \
        --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": "inference-net/Schematron-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inference-net/Schematron-3B with Docker Model Runner:
```
docker model run hf.co/inference-net/Schematron-3B
```

opensporks commited on Sep 5, 2025

Commit

c3be7f0

verified ·

1 Parent(s): 0bcdd1d

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -9

README.md CHANGED Viewed

@@ -68,15 +68,7 @@ We evaluated Schematron's real-world impact on LLM factuality using SimpleQA.
 3. **Structured Extraction**: Schematron extracts JSON data from retrieved pages using the schema
 4. **Answer Synthesis**: Primary LLM produces final answer from structured data
-| Base Model | Configuration | SimpleQA Accuracy |
-|:-----------|:--------------|------------------:|
-| GPT-5 Nano | Solo | 8.54% |
-| GPT-5 Nano | + SERP + Schematron-8B | 64.15% |
-| GPT-5 Nano | + Exa + **Schematron-3B** | **75.47%** |
-| GPT-5 Nano | + Exa + Gemini 2.5 Flash | 80.61% |
-| GPT-5 Nano | + Exa + **Schematron-8B** | **82.87%** |
-| GPT-4.1 | Solo | 41.60% |
-| GPT-4.1 | + Exa + **Schematron-8B** | **85.58%** |
 **Key findings:**
 - Web search paired with JSON extraction improves factuality: Adding Schematron with web retrieval improves GPT-5 Nano's accuracy from 8.54% to 82.87%—nearly a 10x improvement

 3. **Structured Extraction**: Schematron extracts JSON data from retrieved pages using the schema
 4. **Answer Synthesis**: Primary LLM produces final answer from structured data
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6626a246891c75742bd19aaf/h2CA0TpQ1hKDxexGlpdSQ.png)
 **Key findings:**
 - Web search paired with JSON extraction improves factuality: Adding Schematron with web retrieval improves GPT-5 Nano's accuracy from 8.54% to 82.87%—nearly a 10x improvement