Update app.py

app.py

@@ -4,8 +4,8 @@ import numpy as np
 import gradio as gr
 import spaces
 
-tokenizer = AutoTokenizer.from_pretrained("gpt2")
-model = AutoModelForCausalLM.from_pretrained("gpt2")
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
 
 print("Loading finished.")
 
@@ -147,7 +147,7 @@ a:before {
 	text-decoration-line: none;
 	border-radius: 5px;
 	transition: .5s;
-    width: 260px;
+    width: 280px;
     display: flex;
     align-items: center;
     justify-content: space-around;
@@ -207,7 +207,8 @@ def generate_nodes(token_ix, node, step):
     """Recursively generate HTML for the tree nodes."""
     token = tokenizer.decode([token_ix])
     html_content = f" <li> <a href='#' class='{('chosen' if node.table is None else '')}'> <span> <b>{token_ix}:<br>{clean(token)}</b> </span> "
-    html_content += node.table if node.table is not None else ""
+    if node.table is not None:
+        html_content += node.table
     html_content += "</a>"
     if len(node.children.keys()) > 0:
         html_content += "<ul> "
@@ -371,7 +372,7 @@ def get_beam_search_html(input_text, number_steps, number_beams, length_penalty)
         output_scores=True,
         do_sample=False,
     )
-    markdown = "Sequences:"
+    markdown = "Output sequences:"
     decoded_sequences = tokenizer.batch_decode(outputs.sequences)
     for i, sequence in enumerate(decoded_sequences):
         markdown += f"\n- {sequence} ( score {outputs.sequences_scores[i]:.2f})"
@@ -402,11 +403,11 @@ Play with the parameters below to understand how beam search decoding works!
 - **Number of beams**: the number of beams to use
 - **Length penalty**: the length penalty to apply to outputs. `length_penalty` > 0.0 promotes longer sequences, while `length_penalty` < 0.0 encourages shorter sequences.
 """)
-    text = gr.Textbox(label="Sentence to decode from", value="Today is")
+    text = gr.Textbox(label="Sentence to decode from", value="Conclusion: thanks a lot. This article was originally published on")
     with gr.Row():
         steps = gr.Slider(label="Number of steps", minimum=1, maximum=8, step=1, value=4)
         beams = gr.Slider(label="Number of beams", minimum=2, maximum=4, step=1, value=3)
-        length_penalty = gr.Slider(label="Length penalty", minimum=-5, maximum=5, step=0.5, value=1)
+        length_penalty = gr.Slider(label="Length penalty", minimum=-4, maximum=4, step=0.5, value=1)
     button = gr.Button()
     out_html = gr.Markdown()
     out_markdown = gr.Markdown()