chan

app.py

@@ -1,7 +1,74 @@
+## https://www.kaggle.com/code/unravel/fine-tuning-of-a-sql-model
+
+import spaces
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 import gradio as gr
+import torch
+from transformers.utils import logging
+from example_queries import small_query, long_query
+
+logging.set_verbosity_info()
+logger = logging.get_logger("transformers")
+
+model_name='t5-small'
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+original_model = AutoModelForSeq2SeqLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
+original_model.to('cuda')
+
+ft_model_name="cssupport/t5-small-awesome-text-to-sql"
+ft_model = AutoModelForSeq2SeqLM.from_pretrained(ft_model_name, torch_dtype=torch.bfloat16)
+ft_model.to('cuda')
+
+@spaces.GPU
+def translate_text(text):
+   prompt = f"{text}"
+   inputs = tokenizer(prompt, return_tensors='pt')
+   inputs = inputs.to('cuda')
+
+   try:
+        output = tokenizer.decode(
+            original_model.generate(
+                inputs["input_ids"], 
+                max_new_tokens=200,
+            )[0], 
+            skip_special_tokens=True
+        )
+        ft_output = tokenizer.decode(
+            ft_model.generate(
+                inputs["input_ids"], 
+                max_new_tokens=200,
+            )[0], 
+            skip_special_tokens=True
+        )
+        return [output, ft_output]
+   except Exception as e:
+       return f"Error: {str(e)}"
+
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column():
+            prompt = gr.Textbox(
+                value=small_query,
+                lines=8,
+                placeholder="Enter prompt...",
+                label="Prompt"
+            )
+            submit_btn = gr.Button(value="Generate")
+        with gr.Column():
+            orig_output = gr.Textbox(label="OriginalModel", lines=2) 
+            ft_output = gr.Textbox(label="FTModel", lines=8)
+
+    submit_btn.click(
+        translate_text, inputs=[prompt], outputs=[orig_output, ft_output], api_name=False
+    )
+    examples = gr.Examples(
+        examples=[
+            [small_query],
+            [long_query],
+        ],
+        inputs=[prompt],
+    )
 
-def greet(name):
-    return "Hello " + name + "!!"
+demo.launch(show_api=False, share=True, debug=True)
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()

example_queries.py

@@ -0,0 +1,129 @@
+small_query=""" Tables:
+        CREATE TABLE table_name_11 (date VARCHAR, away_team VARCHAR)
+
+        Question:
+        On what Date did the Away team essendon play?
+
+        Answer:"""
+long_query="""Tables:
+
+CREATE TABLE employees (
+
+    EMPLOYEE_ID decimal(6,0),
+
+    FIRST_NAME varchar(20),
+
+    LAST_NAME varchar(25),
+
+    EMAIL varchar(25),
+
+    PHONE_NUMBER varchar(20),
+
+    HIRE_DATE date,
+
+    JOB_ID varchar(10),
+
+    SALARY decimal(8,2),
+
+    COMMISSION_PCT decimal(2,2),
+
+    MANAGER_ID decimal(6,0),
+
+    DEPARTMENT_ID decimal(4,0)
+
+)
+
+
+
+CREATE TABLE jobs (
+
+    JOB_ID varchar(10),
+
+    JOB_TITLE varchar(35),
+
+    MIN_SALARY decimal(6,0),
+
+    MAX_SALARY decimal(6,0)
+
+)
+
+
+
+CREATE TABLE locations (
+
+    LOCATION_ID decimal(4,0),
+
+    STREET_ADDRESS varchar(40),
+
+    POSTAL_CODE varchar(12),
+
+    CITY varchar(30),
+
+    STATE_PROVINCE varchar(25),
+
+    COUNTRY_ID varchar(2)
+
+)
+
+
+
+CREATE TABLE countries (
+
+    COUNTRY_ID varchar(2),
+
+    COUNTRY_NAME varchar(40),
+
+    REGION_ID decimal(10,0)
+
+)
+
+
+
+CREATE TABLE job_history (
+
+    EMPLOYEE_ID decimal(6,0),
+
+    START_DATE date,
+
+    END_DATE date,
+
+    JOB_ID varchar(10),
+
+    DEPARTMENT_ID decimal(4,0)
+
+)
+
+
+
+CREATE TABLE regions (
+
+    REGION_ID decimal(5,0),
+
+    REGION_NAME varchar(25)
+
+)
+
+
+
+CREATE TABLE departments (
+
+    DEPARTMENT_ID decimal(4,0),
+
+    DEPARTMENT_NAME varchar(30),
+
+    MANAGER_ID decimal(6,0),
+
+    LOCATION_ID decimal(4,0)
+
+)
+
+
+
+Question:
+
+For those employees who did not have any job in the past, give me the comparison about the amount of job_id over the job_id , and group by attribute job_id, and list from low to high by the JOB_ID please.
+
+
+
+Answer:
+            """

requirements.txt

@@ -0,0 +1,5 @@
+huggingface_hub==0.22.2
+diffusers
+transformers
+accelerate
+openai