Update space 8

app.py

@@ -2,13 +2,6 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-# Hardcode your space details here
-USERNAME = "sarekuwa"  # Replace with your actual username
-SPACE_NAME = "livecoder"    # Replace with your actual space name
-API_ENDPOINT = f"https://{USERNAME}-{SPACE_NAME}.hf.space/api/predict"
-
-print(f"API Endpoint: {API_ENDPOINT}")
-
 # Load model and tokenizer
 model_name = "microsoft/phi-2"
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
@@ -26,27 +19,30 @@ def generate_response(message):
     if not message.strip():
         return "Please enter a question."
     
-    prompt = f"### Instruction: {message}\n### Response:"
-    
-    inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512)
-    
-    with torch.no_grad():
-        outputs = model.generate(
-            inputs.input_ids,
-            max_new_tokens=256,
-            temperature=0.7,
-            do_sample=True,
-            top_p=0.9,
-            pad_token_id=tokenizer.pad_token_id,
-            eos_token_id=tokenizer.eos_token_id
-        )
+    try:
+        prompt = f"### Instruction: {message}\n### Response:"
+        
+        inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512)
+        
+        with torch.no_grad():
+            outputs = model.generate(
+                inputs.input_ids,
+                max_new_tokens=256,
+                temperature=0.7,
+                do_sample=True,
+                top_p=0.9,
+                pad_token_id=tokenizer.pad_token_id,
+                eos_token_id=tokenizer.eos_token_id
+            )
+        
+        response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
+        return response.strip()
     
-    response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
-    return response.strip()
+    except Exception as e:
+        return f"Error generating response: {str(e)}"
 
-# Create interface
 interface = gr.Interface(
-    fn=generate_response,
+    fn=generate_response,  # Connect function to interface
     inputs=gr.Textbox(label="Input", placeholder="Enter programming question...", lines=3),
     outputs=gr.Textbox(label="Output", lines=10),
     title="LiveCoder API",

requirements.txt

@@ -1,3 +1,4 @@
-torch
-transformers
+torch>=2.0.0
+transformers>=4.35.0
+gradio>=4.0.0
 accelerate