Update app.py

app.py

@@ -1,8 +1,54 @@
-# Use a pipeline as a high-level helper
-from transformers import pipeline
 
-messages = [
-    {"role": "user", "content": "Who are you?"},
+nl2sqlite_template_cn = """You are a SQLite expert. Now you need to read and understand the following [database schema] description,
+as well as the [reference information] that may be used, and use SQLite knowledge to generate SQL statements to answer [user questions].
+[User question]
+{question}
+
+[Database schema]
+{db_schema}
+
+[Reference information]
+{evidence}
+
+[User question]
+{question}
+
+```sql"""
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "XGenerationLab/XiYanSQL-QwenCoder-3B-2502"
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+## dialects -> ['SQLite', 'PostgreSQL', 'MySQL']
+prompt = nl2sqlite_template_cn.format(dialect="", db_schema="", question="", evidence="")
+message = [{'role': 'user', 'content': prompt}]
+
+text = tokenizer.apply_chat_template(
+    message,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    pad_token_id=tokenizer.pad_token_id,
+    eos_token_id=tokenizer.eos_token_id,
+    max_new_tokens=1024,
+    temperature=0.1,
+    top_p=0.8,
+    do_sample=True,
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
 ]
-pipe = pipeline("text-generation", model="defog/llama-3-sqlcoder-8b")
-pipe(messages)
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+