update

app copy.py

@@ -0,0 +1,43 @@
+import gradio as gr
+import spaces
+
+import os
+import gc
+import random
+import warnings
+
+warnings.filterwarnings("ignore")
+
+import numpy as np
+import pandas as pd
+
+pd.set_option("display.max_rows", 500)
+pd.set_option("display.max_columns", 500)
+pd.set_option("display.width", 1000)
+from tqdm.auto import tqdm
+
+import torch
+import torch.nn as nn
+import tokenizers
+import transformers
+
+print(f"tokenizers.__version__: {tokenizers.__version__}")
+print(f"transformers.__version__: {transformers.__version__}")
+print(f"torch.__version__: {torch.__version__}")
+print(f"torch cuda version: {torch.version.cuda}")
+from transformers import AutoTokenizer, AutoConfig
+from transformers import BitsAndBytesConfig, AutoModelForCausalLM, MistralForCausalLM
+from peft import LoraConfig, get_peft_model
+
+
+title = "H2O AI Predict the LLM"
+
+zero = torch.Tensor([0]).cuda()
+print(zero.device) # <-- 'cpu' 🤔
+
+@spaces.GPU
+def greet(n):
+    print(zero.device) # <-- 'cuda:0' 🤗
+    return f"Hello {zero + n} Tensor"
+
+gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text()).launch()

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-import spaces
+# import spaces
 
 import os
 import gc
@@ -32,12 +32,40 @@ from peft import LoraConfig, get_peft_model
 
 title = "H2O AI Predict the LLM"
 
-zero = torch.Tensor([0]).cuda()
-print(zero.device) # <-- 'cpu' 🤔
+#Theme from - https://huggingface.co/spaces/trl-lib/stack-llama/blob/main/app.py
+theme = gr.themes.Monochrome(
+    primary_hue="indigo",
+    secondary_hue="blue",
+    neutral_hue="slate",
+    radius_size=gr.themes.sizes.radius_sm,
+    font=[gr.themes.GoogleFont("Open Sans"), "ui-sans-serif", "system-ui", "sans-serif"],
+)
 
-@spaces.GPU
-def greet(n):
-    print(zero.device) # <-- 'cuda:0' 🤗
-    return f"Hello {zero + n} Tensor"
+def do_submit(question, response):
+    full_text = question + " " + response
+    # result = do_inference(full_text)
+    return "result"
 
-gr.Interface(fn=greet, inputs=gr.Number(), outputs=gr.Text()).launch()
+with gr.Blocks(title=title) as demo: # theme=theme
+    sample_examples = pd.read_csv('sample_examples.csv')
+    example_list = sample_examples[['Question','Response','target']].sample(2).values.tolist()
+    gr.Markdown(f"## {title}")
+    with gr.Row():
+        # with gr.Column(scale=1):
+            # gr.Markdown("### Question and LLM Response")
+            question_text = gr.Textbox(lines=2, placeholder="Question:", label="")
+            response_text = gr.Textbox(lines=2, placeholder="Response:", label="")
+            target_text = gr.Textbox(lines=1, placeholder="Target:", label="", interactive=False , visible=False)
+            llm_num = gr.Textbox(value="", label="LLM #")
+    with gr.Row():
+            sub_btn = gr.Button("Submit")
+            sub_btn.click(fn=do_submit,  inputs=[question_text, response_text], outputs=[llm_num])
+
+    gr.Markdown("## Sample Inputs:")
+    gr.Examples(
+        example_list,
+        [question_text,response_text,target_text],
+        # cache_examples=True,   
+    )
+
+demo.launch(debug=True)