Update app.py

app.py

@@ -1,29 +1,26 @@
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, Conversation
 
-# Specify the model and tokenizer
+# Load your model from Hugging Face Transformers
 model_name = "deepseek-ai/deepseek-math-7b-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
-model.generation_config = GenerationConfig.from_pretrained(model_name)
-model.generation_config.pad_token_id = model.generation_config.eos_token_id
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
-# Function to read text from a file
-def read_input_text(file_path):
-    with open(file_path, 'r', encoding='utf-8') as file:
-        text = file.read()
-    return text.strip()
+# Define a function to use the model
+def math_inference(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt")
+    output = model.generate(**inputs)
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    return response
 
-# Example usage: Replace 'input.txt' with your file path
-input_text = read_input_text('input.txt')
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=math_inference,
+    inputs=gr.Textbox(prompt="Input math question"),
+    outputs=gr.Textbox(prompt="Math answer"),
+    layout="vertical",
+    title="Math Solver"
+)
 
-# Prepare input as a chat message
-messages = [{"role": "user", "content": input_text}]
-input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
-
-# Generate outputs from the model
-outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)
-
-# Decode the generated output
-result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
-print(result)
+# Launch the Gradio interface
+iface.launch()