Upload README.md with huggingface_hub

README.md

@@ -45,6 +45,14 @@ This model is part of the **TRUST-SQL** series, which focuses on building trustw
 
 ## Usage
 
+TrustSQL models are designed for **multi-turn, tool-integrated Text-to-SQL** over unknown schemas. The model explores the database schema via SQL tool calls before generating the final answer.
+
+For the full evaluation pipeline, rollout protocol, reward design, and training scripts, please refer to the GitHub repository:
+
+👉 **[github.com/JaneEyre0530/TrustSQL](https://github.com/JaneEyre0530/TrustSQL)**
+
+### Quick inference
+
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
@@ -57,42 +65,16 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map="auto"
 )
 
-# Example: Text-to-SQL generation
-schema = """
-CREATE TABLE employees (
-    id INT PRIMARY KEY,
-    name VARCHAR(100),
-    department VARCHAR(50),
-    salary DECIMAL(10,2)
-);
-"""
-
-question = "What is the average salary of employees in the Engineering department?"
-
-prompt = f"""Given the following database schema:
-{schema}
-
-Generate a SQL query to answer the question: {question}"""
-
-messages = [{"role": "user", "content": prompt}]
+messages = [{"role": "user", "content": "Your NL2SQL prompt here"}]
 text = tokenizer.apply_chat_template(
     messages,
     tokenize=False,
     add_generation_prompt=True,
-    enable_thinking=False  # Set to True for complex queries requiring reasoning
+    enable_thinking=False
 )
-
 inputs = tokenizer([text], return_tensors="pt").to(model.device)
-outputs = model.generate(
-    **inputs,
-    max_new_tokens=512,
-    temperature=0.7,
-    top_p=0.9,
-)
-response = tokenizer.decode(
-    outputs[0][inputs["input_ids"].shape[1]:],
-    skip_special_tokens=True
-)
+outputs = model.generate(**inputs, max_new_tokens=512)
+response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
 print(response)
 ```