Update app.py

app.py

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