Update app.py

app.py

@@ -1,13 +1,10 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
 
 # Load model and tokenizer
 model_name = "Smilyai-labs/Sam-large-v1-speacil"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model.to(device)
 
 # Chat function
 def respond(message, history):
@@ -17,15 +14,10 @@ def respond(message, history):
         chat_prompt += f"User: {user}\nSam: {bot}\n"
     chat_prompt += f"User: {message}\nSam:"
 
-    inputs = tokenizer(chat_prompt, return_tensors="pt").to(device)
-    outputs = model.generate(
-        **inputs,
-        max_new_tokens=128,
-        temperature=0.7,
-        top_p=0.9,
-        do_sample=True,
-        pad_token_id=tokenizer.eos_token_id
-    )
+    # Tokenize input and generate a response
+    inputs = tokenizer(chat_prompt, return_tensors="pt")
+    outputs = model.generate(inputs["input_ids"], max_length=200, num_return_sequences=1)
+
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     reply = response[len(chat_prompt):].split("\n")[0].strip()