Update app.py

app.py

@@ -1,41 +1,25 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
+from transformers import pipeline
 
-MODEL_ID = "lazarus19/OpenHusky"
-
-tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
-
-model = AutoModelForCausalLM.from_pretrained(
-    MODEL_ID,
-    torch_dtype=torch.float32
+pipe = pipeline(
+    "text-generation",
+    model="lazarus19/OpenHusky"
 )
 
-def generate_response(message):
-    inputs = tokenizer(
+def chat(message):
+    result = pipe(
         message,
-        return_tensors="pt"
-    )
-
-    outputs = model.generate(
-        **inputs,
         max_new_tokens=128,
-        temperature=0.7,
-        do_sample=True
+        do_sample=True,
+        temperature=0.7
     )
 
-    return tokenizer.decode(
-        outputs[0],
-        skip_special_tokens=True
-    )
+    return result[0]["generated_text"]
 
 demo = gr.Interface(
-    fn=generate_response,
-    inputs=gr.Textbox(
-        lines=3,
-        placeholder="Ask OpenHusky..."
-    ),
-    outputs="text",
+    fn=chat,
+    inputs=gr.Textbox(label="Message"),
+    outputs=gr.Textbox(label="Response"),
     title="OpenHusky"
 )