Upload folder using huggingface_hub

util.py

@@ -1,32 +1,7 @@
 from flask import Flask
 import ollama
 
-app = Flask(__name__)
 
-@app.route('/')
-def hello_world():
-    return "<h1>Hello, World!<h1>"
-
-
-@app.route('/list')
-def test_world():
-    from ollama import ListResponse, list
-
-    response: ListResponse = list()
-    ansver = []
-    for model in response.models:
-      ansver.append(f'Name:{model.model}')
-      ansver.append(f'  Size (MB): {(model.size.real / 1024 / 1024):.2f}')
-      if model.details:
-        ansver.append(f'  Format: {model.details.format}')
-        ansver.append(f'  Family:  {model.details.family}')
-        ansver.append(f'  Parameter Size:  {model.details.parameter_size}')
-        ansver.append(f'  Quantization Level:{model.details.quantization_level}')
-    result = [f'<p>{answ}</p>' for answ in ansver ]
-    return '\n'.join(result)
-
-
-@app.route('/ps')
 def ps():
     from ollama import ProcessResponse, chat, ps, pull
     ansver = []
@@ -41,104 +16,10 @@ def ps():
           ansver.append(f'  Details: {model.details}')
           ansver.append(f'  Context length:  {model.context_length}')
           ansver.append(f'\n')
-
-    response: ListResponse = list()
-    for model in response.models:
-      ansver.append(f'Name:{model.model}')
-      ansver.append(f'  Size (MB): {(model.size.real / 1024 / 1024):.2f}')
-      if model.details:
-        ansver.append(f'  Format: {model.details.format}')
-        ansver.append(f'  Family:  {model.details.family}')
-        ansver.append(f'  Parameter Size:  {model.details.parameter_size}')
-        ansver.append(f'  Quantization Level:{model.details.quantization_level}')
     result = [f'<p>{answ}</p>' for answ in ansver ]
     return '\n'.join(result)
 
-@app.route('/time')
-def test_time():
-  from  datetime import datetime
-  from ollama import Client
-  from ollama import chat
-
-  t_start=datetime.now()
-  ansver = []
-  messages = [
-  {
-    'role': 'user',
-    'content': 'Расскажи о себе подробно',
-  },
-  ]
-  response = chat('qwen3:0.6b', messages=messages)
-  ansver.append(f' start {t_start} ')
-  response_time=datetime.now()-t_start
-  ansver.append(f' duration  {response_time} ')
-  #
-  response_len = len(response['message']['content'])
-  ansver.append(f" lehgth {response_len}")
-  response_speed=response_len/int(response_time.seconds)
-  ansver.append(f" token/sek {response_len}")
-  ansver.append(response['message']['content'])
-  result = [f'<p>{answ}</p>' for answ in ansver ]
-  return '\n'.join(result)
-
-
-@app.route('/time8')
-def test_time8():
-  from  datetime import datetime
-  from ollama import Client
-  from ollama import chat
-
-  t_start=datetime.now()
-  ansver = []
-  messages = [
-  {
-    'role': 'user',
-    'content': 'Расскажи о себе подробно',
-  },
-  ]
-  response = chat('qwen3:8b', messages=messages)
-  ansver.append(f' start {t_start} ')
-  response_time=datetime.now()-t_start
-  ansver.append(f' duration  {response_time} ')
-  #
-  response_len = len(response['message']['content'])
-  ansver.append(f" lehgth {response_len}")
-  response_speed=response_len/int(response_time.seconds)
-  ansver.append(f" token/sek {response_len}")
-  ansver.append(response['message']['content'])
-  result = [f'<p>{answ}</p>' for answ in ansver ]
-  return '\n'.join(result)
-
-#@app.route('/time14')
-def test_time14():
-  from  datetime import datetime
-  from ollama import Client
-  from ollama import chat
-
-  t_start=datetime.now()
-  ansver = []
-  messages = [
-  {
-    'role': 'user',
-    'content': 'Расскажи о себе подробно',
-  },
-  ]
-  response = chat('qwen3:14b', messages=messages)
-  ansver.append(f' start {t_start} ')
-  response_time=datetime.now()-t_start
-  ansver.append(f' duration  {response_time} ')
-  #
-  response_len = len(response['message']['content'])
-  ansver.append(f" lehgth {response_len}")
-  response_speed=response_len/int(response_time.seconds)
-  ansver.append(f" token/sek {response_len}")
-  ansver.append(response['message']['content'])
-  result = [f'<p>{answ}</p>' for answ in ansver ]
-  return '\n'.join(result)
-
-
-#@app.route('/time30')
-def test_time30():
+def time_model(model_name='qwen3:0.6b'):
   from  datetime import datetime
   from ollama import Client
   from ollama import chat
@@ -151,7 +32,7 @@ def test_time30():
     'content': 'Расскажи о себе подробно',
   },
   ]
-  response = chat('qwen3:30b', messages=messages)
+  response = chat(model_name, messages=messages)
   ansver.append(f' start {t_start} ')
   response_time=datetime.now()-t_start
   ansver.append(f' duration  {response_time} ')
@@ -164,5 +45,3 @@ def test_time30():
   result = [f'<p>{answ}</p>' for answ in ansver ]
   return '\n'.join(result)
 
-if __name__ == '__main__':
-   app.run(host='0.0.0.0', port="7860")