Update app.py

app.py

@@ -30,85 +30,6 @@ from huggingface_hub import hf_hub_download
 from huggingface_hub import login
 from datasets import load_dataset
 
-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}</s> "
-  prompt += f"[INST] {message} [/INST]"
-  return prompt
-
-def generate(
-    prompt, history, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
-):
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
-    top_p = float(top_p)
-
-    generate_kwargs = dict(
-        temperature=temperature,
-        max_new_tokens=max_new_tokens,
-        top_p=top_p,
-        repetition_penalty=repetition_penalty,
-        do_sample=True,
-        seed=42,
-    )
-
-    formatted_prompt = format_prompt(prompt, history)
-
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
-
-    for response in stream:
-        output += response.token.text
-        yield output
-    return output
-
-
-additional_inputs=[
-    gr.Slider(
-        label="Temperature",
-        value=0.9,
-        minimum=0.0,
-        maximum=1.0,
-        step=0.05,
-        interactive=True,
-        info="Higher values produce more diverse outputs",
-    ),
-    gr.Slider(
-        label="Max new tokens",
-        value=256,
-        minimum=0,
-        maximum=5000,
-        step=64,
-        interactive=True,
-        info="The maximum numbers of new tokens",
-    ),
-    gr.Slider(
-        label="Top-p (nucleus sampling)",
-        value=0.90,
-        minimum=0.0,
-        maximum=1,
-        step=0.05,
-        interactive=True,
-        info="Higher values sample more low-probability tokens",
-    ),
-    gr.Slider(
-        label="Repetition penalty",
-        value=1.2,
-        minimum=1.0,
-        maximum=2.0,
-        step=0.05,
-        interactive=True,
-        info="Penalize repeated tokens",
-    )
-]
 
 #dataset = load_dataset("csv", data_files="./data.csv")
 
@@ -176,12 +97,20 @@ def ccogsphere(name: str, rate: str, celsci: str):
 					  "Name" : ["Video 1", "Video 2", "Video 3", "Video 4", "Video 5"], 
 					  "Views" : [500, 2000, 540, 300, 200], 
 					  "Duration" : [30, 20, 70, 35, 22]})
-        name1=name.split()
+        name1=name.split(":")
+        mess=name1[1]
         try:
-            nam=name1[0]
-            mess=name
+            client = Client("https://osaaso-mistral-7b-instruct.hf.space/")
+            result = client.predict(
+            				mess,	
+            				0,
+            				0,
+            				0,
+            				1,
+            				api_name="/chat"
+            )
+            nam=result.json() #name1[0]
             if name[1]==None:
-                nam="you wrote no messages..."
                 mess="No messages..."
         except:
             nam="No name, write your name followed by a message"