Update app.py

app.py

@@ -1,16 +1,36 @@
 from typing import Iterator
 
 import gradio as gr
-
+import torch
 
 from model import get_input_token_length, run
-MAX_MAX_NEW_TOKENS = 512
+
+DEFAULT_SYSTEM_PROMPT = """\
+You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\
+"""
+MAX_MAX_NEW_TOKENS = 2048
 DEFAULT_MAX_NEW_TOKENS = 1024
-MAX_INPUT_TOKEN_LENGTH = 512
+MAX_INPUT_TOKEN_LENGTH = 4000
+
+DESCRIPTION = """
+# Llama-2 13B Chat
+This Space demonstrates model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta, a Llama 2 model with 13B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
+🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
+🔨 Looking for an even more powerful model? Check out the large [**70B** model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
+🐇 For a smaller model that you can run on many GPUs, check our [7B model demo](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat).
+"""
+
+LICENSE = """
+<p/>
+---
+As a derivate work of [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta,
+this demo is governed by the original [license](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/LICENSE.txt) and [acceptable use policy](https://huggingface.co/spaces/huggingface-projects/llama-2-13b-chat/blob/main/USE_POLICY.md).
+"""
 
 if not torch.cuda.is_available():
     DESCRIPTION += '\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>'
-    
+
+
 def clear_and_save_textbox(message: str) -> tuple[str, str]:
     return '', message
 
@@ -29,6 +49,7 @@ def delete_prev_fn(
         message = ''
     return history, message or ''
 
+
 def generate(
     message: str,
     history_with_input: list[tuple[str, str]],
@@ -51,28 +72,20 @@ def generate(
     for response in generator:
         yield history + [(message, response)]
 
-def preprocess(sample):
-    first_sentences = [sample["prompt"]] * 5
-    second_sentences = [sample[option] for option in "ABCDE"]
-    tokenized_sentences = tokenizer(first_sentences, second_sentences, truncation=True, padding=True, return_tensors="pt")
-    sample["input_ids"] = tokenized_sentences["input_ids"]
-    sample["attention_mask"] = tokenized_sentences["attention_mask"]
-    return sample
-
-# Define the prediction function
-def predict(data):
-    inputs = torch.stack(data["input_ids"])
-    masks = torch.stack(data["attention_mask"])
-    with torch.no_grad():
-        logits = model(inputs, attention_mask=masks).logits
-    predictions_as_ids = torch.argsort(-logits, dim=1)
-    answers = np.array(list("ABCDE"))[predictions_as_ids.tolist()]
-    return ["".join(i) for i in answers[:, :3]]
+
+def process_example(message: str) -> tuple[str, list[tuple[str, str]]]:
+    generator = generate(message, [], DEFAULT_SYSTEM_PROMPT, 1024, 1, 0.95, 50)
+    for x in generator:
+        pass
+    return '', x
+
+
 def check_input_token_length(message: str, chat_history: list[tuple[str, str]], system_prompt: str) -> None:
     input_token_length = get_input_token_length(message, chat_history, system_prompt)
     if input_token_length > MAX_INPUT_TOKEN_LENGTH:
         raise gr.Error(f'The accumulated input is too long ({input_token_length} > {MAX_INPUT_TOKEN_LENGTH}). Clear your chat history and try again.')
 
+
 with gr.Blocks(css='style.css') as demo:
     gr.Markdown(DESCRIPTION)
     gr.DuplicateButton(value='Duplicate Space for private use',
@@ -131,18 +144,20 @@ with gr.Blocks(css='style.css') as demo:
             value=50,
         )
 
-    gr.Interface(
-        
-        fn=predict,
-        inputs=gr.Interface.DataType.json,
-        outputs=gr.outputs.Label(num_top_classes=3),
-        live=True,
+    gr.Examples(
         examples=[
-            {"prompt": "This is the prompt", "A": "Option A text", "B": "Option B text", "C": "Option C text", "D": "Option D text", "E": "Option E text"}
+            'Hello there! How are you doing?',
+            'Can you explain briefly to me what is the Python programming language?',
+            'Explain the plot of Cinderella in a sentence.',
+            'How many hours does it take a man to eat a Helicopter?',
+            "Write a 100-word article on 'Benefits of Open-Source in AI research'",
         ],
-        title="LLM Science Exam Demo",
-        description="Enter the prompt and options (A to E) below and get predictions.",
+        inputs=textbox,
+        outputs=[textbox, chatbot],
+        fn=process_example,
+        cache_examples=True,
     )
+
     gr.Markdown(LICENSE)
 
     textbox.submit(
@@ -258,3 +273,4 @@ with gr.Blocks(css='style.css') as demo:
     )
 
 demo.queue(max_size=20).launch()
+