Update app.py

app.py

@@ -1,26 +1,16 @@
-from huggingface_hub import InferenceClient
 import gradio as gr
+from huggingface_hub import InferenceClient
+
+client = InferenceClient("mistralai/Mistral-7B-v0.1")
+
+# Fixed temperature value
+fixed_temperature = 0.9  # You can adjust this value as needed
 
-client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
-
-def format_prompt(message, history):
-  prompt = "<s>"
-  for user_prompt, bot_response in history:
-    prompt += f"[INST] {user_prompt} [/INST]"
-    prompt += f" {bot_response} "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
-
-def generate(
-    prompt, history, temperature=0.3, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
-):
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
+def generate(prompt, max_new_tokens=6056, top_p=0.95, repetition_penalty=1.0):
     top_p = float(top_p)
 
     generate_kwargs = dict(
-        temperature=temperature,
+        temperature=fixed_temperature,
         max_new_tokens=max_new_tokens,
         top_p=top_p,
         repetition_penalty=repetition_penalty,
@@ -28,7 +18,7 @@ def generate(
         seed=42,
     )
 
-    formatted_prompt = format_prompt(prompt, history)
+    formatted_prompt = f"<s>[INST] {prompt} [/INST]"
 
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
@@ -38,11 +28,12 @@ def generate(
         yield output
     return output
 
-demo = gr.ChatInterface(fn=generate, 
-                        title="Mistralai-Mistral-7B-Instruct Chat",
-                        retry_btn=None,
-                        undo_btn=None,
-                        clear_btn=None
-                       )
+iface = gr.Interface(
+    fn=generate,
+    inputs="text",
+    outputs="text",
+    title="Mistralai-Mistral-7B-Instruct Chat",
+    live=False  # Set live to False to add a "Submit" button
+)
 
-demo.queue().launch()
+iface.launch()