Update

app-ngrok.py

@@ -8,6 +8,12 @@ import platform
 
 print(f"Running on {platform.system()}")
 
+quantized_model = "richardr1126/spider-skeleton-wizard-coder-ggml"
+merged_model = "richardr1126/spider-skeleton-wizard-coder-merged"
+initial_model = "WizardLM/WizardCoder-15B-V1.0"
+lora_model = "richardr1126/spider-skeleton-wizard-coder-qlora"
+dataset = "richardr1126/spider-skeleton-context-instruct"
+
 def format(text):
     # Split the text by "|", and get the last element in the list which should be the final query
     try:
@@ -87,6 +93,12 @@ with gr.Blocks(theme='gradio/soft') as demo:
     run_button = gr.Button("Generate SQL", variant="primary")
     run_button.click(fn=generate, inputs=[input_text, db_info, temperature, top_p, top_k, repetition_penalty], outputs=output_box, api_name="txt2sql")
     
+    info = gr.HTML(f"""
+        <p>🌐 Leveraging the <a href='https://huggingface.co/{quantized_model}'><strong>4-bit GGML version</strong></a> of <a href='https://huggingface.co/{merged_model}'><strong>{merged_model}</strong></a> model.</p>
+        <p>🔗 How it's made: <a href='https://huggingface.co/{initial_model}'><strong>{initial_model}</strong></a> was finetuned to create <a href='https://huggingface.co/{lora_model}'><strong>{lora_model}</strong></a>, then merged together to create <a href='https://huggingface.co/{merged_model}'><strong>{merged_model}</strong></a>.</p>
+        <p>📉 Fine-tuning was performed using QLoRA techniques on the <a href='https://huggingface.co/datasets/{dataset}'><strong>{dataset}</strong></a> dataset. You can view training metrics on the <a href='https://huggingface.co/{lora_model}'><strong>QLoRa adapter HF Repo</strong></a>.</p>
+    """)
+
     with gr.Accordion("Examples", open=True):
         examples = gr.Examples([
             ["What is the average, minimum, and maximum age of all singers from France?", "| stadium : stadium_id , location , name , capacity , highest , lowest , average | singer : singer_id , name , country , song_name , song_release_year , age , is_male | concert : concert_id , concert_name , theme , stadium_id , year | singer_in_concert : concert_id , singer_id | concert.stadium_id = stadium.stadium_id | singer_in_concert.singer_id = singer.singer_id | singer_in_concert.concert_id = concert.concert_id |"],
@@ -94,21 +106,8 @@ with gr.Blocks(theme='gradio/soft') as demo:
             ["What are the number of concerts that occurred in the stadium with the largest capacity ?", "| stadium : stadium_id , location , name , capacity , highest , lowest , average | singer : singer_id , name , country , song_name , song_release_year , age , is_male | concert : concert_id , concert_name , theme , stadium_id , year | singer_in_concert : concert_id , singer_id | concert.stadium_id = stadium.stadium_id | singer_in_concert.singer_id = singer.singer_id | singer_in_concert.concert_id = concert.concert_id |"],
             ["How many male singers performed in concerts in the year 2023?", "| stadium : stadium_id , location , name , capacity , highest , lowest , average | singer : singer_id , name , country , song_name , song_release_year , age , is_male | concert : concert_id , concert_name , theme , stadium_id , year | singer_in_concert : concert_id , singer_id | concert.stadium_id = stadium.stadium_id | singer_in_concert.singer_id = singer.singer_id | singer_in_concert.concert_id = concert.concert_id |"],
             ["List the names of all singers who performed in a concert with the theme 'Rock'", "| stadium : stadium_id , location , name , capacity , highest , lowest , average | singer : singer_id , name , country , song_name , song_release_year , age , is_male | concert : concert_id , concert_name , theme , stadium_id , year | singer_in_concert : concert_id , singer_id | concert.stadium_id = stadium.stadium_id | singer_in_concert.singer_id = singer.singer_id | singer_in_concert.concert_id = concert.concert_id |"]
-        ], inputs=[input_text, db_info, temperature, top_p, top_k, repetition_penalty], fn=generate, cache_examples=False if platform.system() == "Windows" or platform.system() == "Darwin" else True, outputs=output_box)
+        ], inputs=[input_text, db_info, 0.0, top_p, top_k, repetition_penalty], fn=generate, cache_examples=False if platform.system() == "Windows" or platform.system() == "Darwin" else True, outputs=output_box)
 
-    quantized_model = "richardr1126/spider-skeleton-wizard-coder-ggml"
-    merged_model = "richardr1126/spider-skeleton-wizard-coder-merged"
-    initial_model = "WizardLM/WizardCoder-15B-V1.0"
-    lora_model = "richardr1126/spider-skeleton-wizard-coder-qlora"
-    dataset = "richardr1126/spider-skeleton-context-instruct"
-    
-    footer = gr.HTML(f"""
-        <p>🛠️ If you want you can <strong>duplicate this Space</strong>, then change the HF_MODEL_REPO spaces env varaible to use any GGML model.</p>
-        <p>🌐 Leveraging the <a href='https://huggingface.co/{quantized_model}'><strong>4-bit GGML version</strong></a> of <a href='https://huggingface.co/{merged_model}'><strong>{merged_model}</strong></a> model.</p>
-        <p>🔗 How it's made: <a href='https://huggingface.co/{initial_model}'><strong>{initial_model}</strong></a> was finetuned to create <a href='https://huggingface.co/{lora_model}'><strong>{lora_model}</strong></a>, then merged together to create <a href='https://huggingface.co/{merged_model}'><strong>{merged_model}</strong></a>.</p>
-        <p>📉 Fine-tuning was performed using QLoRA techniques on the <a href='https://huggingface.co/datasets/{dataset}'><strong>{dataset}</strong></a> dataset. You can view training metrics on the <a href='https://huggingface.co/{lora_model}'><strong>QLoRa adapter HF Repo</strong></a>.</p>
-
-    """)
 
     readme_content = requests.get(f"https://huggingface.co/{merged_model}/raw/main/README.md").text
     readme_content = re.sub('---.*?---', '', readme_content, flags=re.DOTALL) #Remove YAML front matter