Create app.py

app.py

@@ -0,0 +1,22 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+import gradio as gr
+
+model_name = "TheBloke/MelloGPT-AWQ"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    trust_remote_code=True,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def chat(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
+    output = model.generate(**inputs, max_new_tokens=150)
+    reply = tokenizer.decode(output[0], skip_special_tokens=True)
+    return reply
+
+gr.Interface(fn=chat, inputs="text", outputs="text").launch()
+