Update app.py

app.py

@@ -6,7 +6,7 @@ from pynvml import *
 nvmlInit()
 gpu_h = nvmlDeviceGetHandleByIndex(0)
 ctx_limit = 1024
-title = "RWKV-4-Raven-7B-v9-Eng99%-Other1%-20230412-ctx8192"
+title = "RWKV-4-Raven-7B-v10-Eng99%-Other1%-20230418-ctx8192"
 
 os.environ["RWKV_JIT_ON"] = '1'
 os.environ["RWKV_CUDA_ON"] = '1' # if '1' then use CUDA kernel for seq mode (much faster)
@@ -91,13 +91,13 @@ def evaluate(
     yield out_str.strip()
 
 examples = [
-    ["Tell me about ravens.", "", 150, 1.2, 0.5, 0.3, 0.3],
-    ["Write a python function to mine 1 BTC, with details and comments.", "", 150, 1.2, 0.5, 0.3, 0.3],
-    ["Write a song about ravens.", "", 150, 1.2, 0.5, 0.3, 0.3],
-    ["Explain the following metaphor: Life is like cats.", "", 150, 1.2, 0.5, 0.3, 0.3],
-    ["Write a story using the following information", "A man named Alex chops a tree down", 150, 1.2, 0.5, 0.3, 0.3],
-    ["Generate a list of adjectives that describe a person as brave.", "", 150, 1.2, 0.5, 0.3, 0.3],
-    ["You have $100, and your goal is to turn that into as much money as possible with AI and Machine Learning. Please respond with detailed plan.", "", 150, 1.2, 0.5, 0.3, 0.3],
+    ["Tell me about ravens.", "", 150, 1.2, 0.5, 0.4, 0.4],
+    ["Write a python function to mine 1 BTC, with details and comments.", "", 150, 1.2, 0.5, 0.4, 0.4],
+    ["Write a song about ravens.", "", 150, 1.2, 0.5, 0.4, 0.4],
+    ["Explain the following metaphor: Life is like cats.", "", 150, 1.2, 0.5, 0.4, 0.4],
+    ["Write a story using the following information", "A man named Alex chops a tree down", 150, 1.2, 0.5, 0.4, 0.4],
+    ["Generate a list of adjectives that describe a person as brave.", "", 150, 1.2, 0.5, 0.4, 0.4],
+    ["You have $100, and your goal is to turn that into as much money as possible with AI and Machine Learning. Please respond with detailed plan.", "", 150, 1.2, 0.5, 0.4, 0.4],
 ]
 
 ##########################################################################
@@ -250,8 +250,8 @@ with gr.Blocks(title=title) as demo:
                 token_count = gr.Slider(10, 200, label="Max Tokens", step=10, value=150)
                 temperature = gr.Slider(0.2, 2.0, label="Temperature", step=0.1, value=1.2)
                 top_p = gr.Slider(0.0, 1.0, label="Top P", step=0.05, value=0.5)
-                presence_penalty = gr.Slider(0.0, 1.0, label="Presence Penalty", step=0.1, value=0.3)
-                count_penalty = gr.Slider(0.0, 1.0, label="Count Penalty", step=0.1, value=0.3)
+                presence_penalty = gr.Slider(0.0, 1.0, label="Presence Penalty", step=0.1, value=0.4)
+                count_penalty = gr.Slider(0.0, 1.0, label="Count Penalty", step=0.1, value=0.4)
             with gr.Column():
                 with gr.Row():
                     submit = gr.Button("Submit", variant="primary")
@@ -280,8 +280,8 @@ with gr.Blocks(title=title) as demo:
                 prompt = gr.Textbox(lines=10, max_lines=50, label="Scenario", value=chat_intro)
                 temperature = gr.Slider(0.2, 2.0, label="Temperature", step=0.1, value=1.2)
                 top_p = gr.Slider(0.0, 1.0, label="Top P", step=0.05, value=0.5)
-                presence_penalty = gr.Slider(0.0, 1.0, label="Presence Penalty", step=0.1, value=0.3)
-                count_penalty = gr.Slider(0.0, 1.0, label="Count Penalty", step=0.1, value=0.3)
+                presence_penalty = gr.Slider(0.0, 1.0, label="Presence Penalty", step=0.1, value=0.4)
+                count_penalty = gr.Slider(0.0, 1.0, label="Count Penalty", step=0.1, value=0.4)
         chat_inputs = [
             prompt,
             user_name,