Create app.py

app.py

@@ -0,0 +1,24 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "dphn/Dolphin3.0-Llama3.1-8B"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def chat(message, history):
+    inputs = tokenizer.apply_chat_template(
+        history + [{"role": "user", "content": message}],
+        return_tensors="pt"
+    ).to(model.device)
+    outputs = model.generate(inputs, max_new_tokens=512)
+    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    history.append({"role": "assistant", "content": reply})
+    return reply, history
+
+gr.ChatInterface(fn=chat, title="Dolphin 3.0 Chat").launch()