add streamer

app.py

@@ -1,3 +1,16 @@
 import gradio as gr
 
-gr.load("models/google/gemma-7b").launch()
+from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer
+
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
+model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
+streamer = TextStreamer(tokenizer)
+
+
+def generate(inputs):
+    inputs = tokenizer([inputs], return_tensors="pt")
+    yield model.generate(**inputs, streamer=streamer)
+
+
+app = gr.ChatInterface(generate)
+app.launch(debug=True)

requirements.txt

@@ -0,0 +1,2 @@
+torch
+git+https://github.com/huggingface/transformers/