Uploading FoodExtract demo app.py

app.py

@@ -3,14 +3,14 @@
 import time
 import transformers
 import torch
-import spaces
+import spaces # Optional: run our model on the GPU (this will be much faster inference)
 
 import gradio as gr
 
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers import pipeline
 
-@spaces.GPU
+@spaces.GPU # Optional: run our model on the GPU (this will be much faster inference)
 def pred_on_text(input_text):
     start_time = time.time()
 
@@ -26,6 +26,7 @@ def pred_on_text(input_text):
     return generated_text, raw_output, total_time
 
 # Load the model (from our Hugging Face Repo)
+# Note: You may have to replace my username `mrdbourke` for your own
 MODEL_PATH = "mrdbourke/FoodExtract-gemma-3-270m-fine-tune-v1"
 
 # Load the model into a pipeline
@@ -36,6 +37,7 @@ loaded_model = AutoModelForCausalLM.from_pretrained(
     attn_implementation="eager"
 )
 
+# Load the tokenizer
 tokenizer = AutoTokenizer.from_pretrained(
     MODEL_PATH
 )
@@ -46,19 +48,24 @@ loaded_model_pipeline = pipeline("text-generation",
                                  tokenizer=tokenizer)
 
 # Create the demo
-description = """Extract food and drink items from text with a fine-tuned SLM (Small Language Model).
+description = """Extract food and drink items from text with a fine-tuned SLM (Small Language Model) or more specifically a fine-tuned [Gemma 3 270M](https://huggingface.co/google/gemma-3-270m-it).
+
+Our model has been fine-tuned on the [FoodExtract-1k dataset](https://huggingface.co/datasets/mrdbourke/FoodExtract-1k). 
 
 * Input (str): Raw text strings or image captions (e.g. "A photo of a dog sitting on a beach" or "A breakfast plate with bacon, eggs and toast")
 * Output (str): Generated text with food/not_food classification as well as noun extracted food and drink items and various food tags.
 
 For example:
 
-Input: "For breakfast I had eggs, bacon and toast and a glass of orange juice"
-Output: 
+* Input: "For breakfast I had eggs, bacon and toast and a glass of orange juice"
+* Output: 
+
+```
 food_or_drink: 1
 tags: fi, di
 foods: eggs, bacon, toast
 drinks: orange juice
+```
 """
 
 demo = gr.Interface(fn=pred_on_text,