Make the code more like PEP8

Also add torch and torchaudio back to the requirements, as silero needs them. Silero's requirements.txt should be everything needed to run the tests

api-example-stream.py

@@ -17,6 +17,7 @@ def random_hash():
     letters = string.ascii_lowercase + string.digits
     return ''.join(random.choice(letters) for i in range(9))
 
+
 async def run(context):
     server = "127.0.0.1"
     params = {
@@ -69,6 +70,7 @@ async def run(context):
 
 prompt = "What I would like to say is the following: "
 
+
 async def get_result():
     async for response in run(prompt):
         # Print intermediate steps

convert-to-flexgen.py

@@ -17,6 +17,7 @@ parser = argparse.ArgumentParser(formatter_class=lambda prog: argparse.HelpForma
 parser.add_argument('MODEL', type=str, default=None, nargs='?', help="Path to the input model.")
 args = parser.parse_args()
 
+
 def disable_torch_init():
     """
     Disable the redundant torch default initialization to accelerate model creation.
@@ -31,12 +32,14 @@ def disable_torch_init():
     torch_layer_norm_init_backup = torch.nn.LayerNorm.reset_parameters
     setattr(torch.nn.LayerNorm, "reset_parameters", lambda self: None)
 
+
 def restore_torch_init():
     """Rollback the change made by disable_torch_init."""
     import torch
     setattr(torch.nn.Linear, "reset_parameters", torch_linear_init_backup)
     setattr(torch.nn.LayerNorm, "reset_parameters", torch_layer_norm_init_backup)
 
+
 if __name__ == '__main__':
     path = Path(args.MODEL)
     model_name = path.name

download-model.py

@@ -29,6 +29,7 @@ parser.add_argument('--clean', action='store_true', help='Does not resume the pr
 parser.add_argument('--check', action='store_true', help='Validates the checksums of model files.')
 args = parser.parse_args()
 
+
 def get_file(url, output_folder):
     filename = Path(url.rsplit('/', 1)[1])
     output_path = output_folder / filename
@@ -54,6 +55,7 @@ def get_file(url, output_folder):
                 t.update(len(data))
                 f.write(data)
 
+
 def sanitize_branch_name(branch_name):
     pattern = re.compile(r"^[a-zA-Z0-9._-]+$")
     if pattern.match(branch_name):
@@ -61,6 +63,7 @@ def sanitize_branch_name(branch_name):
     else:
         raise ValueError("Invalid branch name. Only alphanumeric characters, period, underscore and dash are allowed.")
 
+
 def select_model_from_default_options():
     models = {
         "OPT 6.7B": ("facebook", "opt-6.7b", "main"),
@@ -106,6 +109,7 @@ EleutherAI/pythia-1.4b-deduped
 
     return model, branch
 
+
 def get_download_links_from_huggingface(model, branch):
     base = "https://huggingface.co"
     page = f"/api/models/{model}/tree/{branch}?cursor="
@@ -172,9 +176,11 @@ def get_download_links_from_huggingface(model, branch):
 
     return links, sha256, is_lora
 
+
 def download_files(file_list, output_folder, num_threads=8):
     thread_map(lambda url: get_file(url, output_folder), file_list, max_workers=num_threads, disable=True)
 
+
 if __name__ == '__main__':
     model = args.MODEL
     branch = args.branch

extensions/api/script.py

@@ -9,6 +9,7 @@ params = {
     'port': 5000,
 }
 
+
 class Handler(BaseHTTPRequestHandler):
     def do_GET(self):
         if self.path == '/api/v1/model':
@@ -32,7 +33,7 @@ class Handler(BaseHTTPRequestHandler):
             self.end_headers()
 
             prompt = body['prompt']
-            prompt_lines = [l.strip() for l in prompt.split('\n')]
+            prompt_lines = [k.strip() for k in prompt.split('\n')]
 
             max_context = body.get('max_context_length', 2048)
 
@@ -95,5 +96,6 @@ def run_server():
         print(f'Starting KoboldAI compatible api at http://{server_addr[0]}:{server_addr[1]}/api')
     server.serve_forever()
 
+
 def setup():
     Thread(target=run_server, daemon=True).start()

extensions/character_bias/script.py

@@ -5,6 +5,7 @@ params = {
     "bias string": " *I am so happy*",
 }
 
+
 def input_modifier(string):
     """
     This function is applied to your text inputs before
@@ -13,6 +14,7 @@ def input_modifier(string):
 
     return string
 
+
 def output_modifier(string):
     """
     This function is applied to the model outputs.
@@ -20,6 +22,7 @@ def output_modifier(string):
 
     return string
 
+
 def bot_prefix_modifier(string):
     """
     This function is only applied in chat mode. It modifies
@@ -27,11 +30,12 @@ def bot_prefix_modifier(string):
     behavior.
     """
 
-    if params['activate'] == True:
+    if params['activate']:
         return f'{string} {params["bias string"].strip()} '
     else:
         return string
 
+
 def ui():
     # Gradio elements
     activate = gr.Checkbox(value=params['activate'], label='Activate character bias')

extensions/elevenlabs_tts/script.py

@@ -22,6 +22,8 @@ if not shared.args.no_stream:
     raise ValueError
 
 # Check if the API is valid and refresh the UI accordingly.
+
+
 def check_valid_api():
 
     global user, user_info, params
@@ -29,7 +31,7 @@ def check_valid_api():
     user = ElevenLabsUser(params['api_key'])
     user_info = user._get_subscription_data()
     print('checking api')
-    if params['activate'] == False:
+    if not params['activate']:
         return gr.update(value='Disconnected')
     elif user_info is None:
         print('Incorrect API Key')
@@ -39,6 +41,8 @@ def check_valid_api():
         return gr.update(value='Connected')
 
 # Once the API is verified, get the available voices and update the dropdown list
+
+
 def refresh_voices():
 
     global user, user_info
@@ -51,11 +55,13 @@ def refresh_voices():
     else:
         return
 
+
 def remove_surrounded_chars(string):
     # this expression matches to 'as few symbols as possible (0 upwards) between any asterisks' OR
     # 'as few symbols as possible (0 upwards) between an asterisk and the end of the string'
     return re.sub('\*[^\*]*?(\*|$)', '', string)
 
+
 def input_modifier(string):
     """
     This function is applied to your text inputs before
@@ -64,6 +70,7 @@ def input_modifier(string):
 
     return string
 
+
 def output_modifier(string):
     """
     This function is applied to the model outputs.
@@ -71,9 +78,9 @@ def output_modifier(string):
 
     global params, wav_idx, user, user_info
 
-    if params['activate'] == False:
+    if not params['activate']:
         return string
-    elif user_info == None:
+    elif user_info is None:
         return string
 
     string = remove_surrounded_chars(string)
@@ -94,6 +101,7 @@ def output_modifier(string):
     wav_idx += 1
     return string
 
+
 def ui():
 
     # Gradio elements

extensions/google_translate/script.py

@@ -7,6 +7,7 @@ params = {
 
 language_codes = {'Afrikaans': 'af', 'Albanian': 'sq', 'Amharic': 'am', 'Arabic': 'ar', 'Armenian': 'hy', 'Azerbaijani': 'az', 'Basque': 'eu', 'Belarusian': 'be', 'Bengali': 'bn', 'Bosnian': 'bs', 'Bulgarian': 'bg', 'Catalan': 'ca', 'Cebuano': 'ceb', 'Chinese (Simplified)': 'zh-CN', 'Chinese (Traditional)': 'zh-TW', 'Corsican': 'co', 'Croatian': 'hr', 'Czech': 'cs', 'Danish': 'da', 'Dutch': 'nl', 'English': 'en', 'Esperanto': 'eo', 'Estonian': 'et', 'Finnish': 'fi', 'French': 'fr', 'Frisian': 'fy', 'Galician': 'gl', 'Georgian': 'ka', 'German': 'de', 'Greek': 'el', 'Gujarati': 'gu', 'Haitian Creole': 'ht', 'Hausa': 'ha', 'Hawaiian': 'haw', 'Hebrew': 'iw', 'Hindi': 'hi', 'Hmong': 'hmn', 'Hungarian': 'hu', 'Icelandic': 'is', 'Igbo': 'ig', 'Indonesian': 'id', 'Irish': 'ga', 'Italian': 'it', 'Japanese': 'ja', 'Javanese': 'jw', 'Kannada': 'kn', 'Kazakh': 'kk', 'Khmer': 'km', 'Korean': 'ko', 'Kurdish': 'ku', 'Kyrgyz': 'ky', 'Lao': 'lo', 'Latin': 'la', 'Latvian': 'lv', 'Lithuanian': 'lt', 'Luxembourgish': 'lb', 'Macedonian': 'mk', 'Malagasy': 'mg', 'Malay': 'ms', 'Malayalam': 'ml', 'Maltese': 'mt', 'Maori': 'mi', 'Marathi': 'mr', 'Mongolian': 'mn', 'Myanmar (Burmese)': 'my', 'Nepali': 'ne', 'Norwegian': 'no', 'Nyanja (Chichewa)': 'ny', 'Pashto': 'ps', 'Persian': 'fa', 'Polish': 'pl', 'Portuguese (Portugal, Brazil)': 'pt', 'Punjabi': 'pa', 'Romanian': 'ro', 'Russian': 'ru', 'Samoan': 'sm', 'Scots Gaelic': 'gd', 'Serbian': 'sr', 'Sesotho': 'st', 'Shona': 'sn', 'Sindhi': 'sd', 'Sinhala (Sinhalese)': 'si', 'Slovak': 'sk', 'Slovenian': 'sl', 'Somali': 'so', 'Spanish': 'es', 'Sundanese': 'su', 'Swahili': 'sw', 'Swedish': 'sv', 'Tagalog (Filipino)': 'tl', 'Tajik': 'tg', 'Tamil': 'ta', 'Telugu': 'te', 'Thai': 'th', 'Turkish': 'tr', 'Ukrainian': 'uk', 'Urdu': 'ur', 'Uzbek': 'uz', 'Vietnamese': 'vi', 'Welsh': 'cy', 'Xhosa': 'xh', 'Yiddish': 'yi', 'Yoruba': 'yo', 'Zulu': 'zu'}
 
+
 def input_modifier(string):
     """
     This function is applied to your text inputs before
@@ -15,6 +16,7 @@ def input_modifier(string):
 
     return GoogleTranslator(source=params['language string'], target='en').translate(string)
 
+
 def output_modifier(string):
     """
     This function is applied to the model outputs.
@@ -22,6 +24,7 @@ def output_modifier(string):
 
     return GoogleTranslator(source='en', target=params['language string']).translate(string)
 
+
 def bot_prefix_modifier(string):
     """
     This function is only applied in chat mode. It modifies
@@ -31,6 +34,7 @@ def bot_prefix_modifier(string):
 
     return string
 
+
 def ui():
     # Finding the language name from the language code to use as the default value
     language_name = list(language_codes.keys())[list(language_codes.values()).index(params['language string'])]

extensions/llama_prompts/script.py

@@ -4,12 +4,14 @@ import pandas as pd
 
 df = pd.read_csv("https://raw.githubusercontent.com/devbrones/llama-prompts/main/prompts/prompts.csv")
 
+
 def get_prompt_by_name(name):
     if name == 'None':
         return ''
     else:
         return df[df['Prompt name'] == name].iloc[0]['Prompt'].replace('\\n', '\n')
 
+
 def ui():
     if not shared.is_chat():
         choices = ['None'] + list(df['Prompt name'])

extensions/sd_api_pictures/script.py

@@ -30,12 +30,15 @@ streaming_state = shared.args.no_stream # remember if chat streaming was enabled
 picture_response = False  # specifies if the next model response should appear as a picture
 pic_id = 0
 
+
 def remove_surrounded_chars(string):
     # this expression matches to 'as few symbols as possible (0 upwards) between any asterisks' OR
     # 'as few symbols as possible (0 upwards) between an asterisk and the end of the string'
     return re.sub('\*[^\*]*?(\*|$)', '', string)
 
 # I don't even need input_hijack for this as visible text will be commited to history as the unmodified string
+
+
 def input_modifier(string):
     """
     This function is applied to your text inputs before
@@ -62,6 +65,8 @@ def input_modifier(string):
     return string
 
 # Get and save the Stable Diffusion-generated picture
+
+
 def get_SD_pictures(description):
 
     global params, pic_id
@@ -101,6 +106,8 @@ def get_SD_pictures(description):
 
 # TODO: how do I make the UI history ignore the resulting pictures (I don't want HTML to appear in history)
 # and replace it with 'text' for the purposes of logging?
+
+
 def output_modifier(string):
     """
     This function is applied to the model outputs.
@@ -130,6 +137,7 @@ def output_modifier(string):
     shared.args.no_stream = streaming_state
     return image + "\n" + text
 
+
 def bot_prefix_modifier(string):
     """
     This function is only applied in chat mode. It modifies
@@ -139,10 +147,12 @@ def bot_prefix_modifier(string):
 
     return string
 
+
 def force_pic():
     global picture_response
     picture_response = True
 
+
 def ui():
 
     # Gradio elements

extensions/send_pictures/script.py

@@ -17,11 +17,13 @@ input_hijack = {
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float32).to("cpu")
 
+
 def caption_image(raw_image):
     inputs = processor(raw_image.convert('RGB'), return_tensors="pt").to("cpu", torch.float32)
     out = model.generate(**inputs, max_new_tokens=100)
     return processor.decode(out[0], skip_special_tokens=True)
 
+
 def generate_chat_picture(picture, name1, name2):
     text = f'*{name1} sends {name2} a picture that contains the following: "{caption_image(picture)}"*'
     # lower the resolution of sent images for the chat, otherwise the log size gets out of control quickly with all the base64 values in visible history
@@ -32,6 +34,7 @@ def generate_chat_picture(picture, name1, name2):
     visible_text = f'<img src="data:image/jpeg;base64,{img_str}" alt="{text}">'
     return text, visible_text
 
+
 def ui():
     picture_select = gr.Image(label='Send a picture', type='pil')
 

extensions/silero_tts/requirements.txt

@@ -1,4 +1,5 @@
 ipython
+num2words
 omegaconf
 pydub
 PyYAML

extensions/silero_tts/script.py

@@ -1,14 +1,16 @@
-import re
 import time
 from pathlib import Path
 
 import gradio as gr
-import modules.chat as chat
-import modules.shared as shared
 import torch
+from extensions.silero_tts import tts_preprocessor
+from modules import chat, shared
+from modules.html_generator import chat_html_wrapper
+
 
 torch._C._jit_set_profiling_mode(False)
 
+
 params = {
     'activate': True,
     'speaker': 'en_56',
@@ -37,26 +39,25 @@ table = str.maketrans({
     '"': """,
 })
 
+
 def xmlesc(txt):
     return txt.translate(table)
 
+
 def load_model():
     model, example_text = torch.hub.load(repo_or_dir='snakers4/silero-models', model='silero_tts', language=params['language'], speaker=params['model_id'])
     model.to(params['device'])
     return model
 model = load_model()
 
-def remove_surrounded_chars(string):
-    # this expression matches to 'as few symbols as possible (0 upwards) between any asterisks' OR
-    # 'as few symbols as possible (0 upwards) between an asterisk and the end of the string'
-    return re.sub('\*[^\*]*?(\*|$)','',string)
 
-def remove_tts_from_history(name1, name2):
+def remove_tts_from_history(name1, name2, mode):
     for i, entry in enumerate(shared.history['internal']):
         shared.history['visible'][i] = [shared.history['visible'][i][0], entry[1]]
-    return chat.generate_chat_output(shared.history['visible'], name1, name2, shared.character)
+    return chat_html_wrapper(shared.history['visible'], name1, name2, mode)
 
-def toggle_text_in_history(name1, name2):
+
+def toggle_text_in_history(name1, name2, mode):
     for i, entry in enumerate(shared.history['visible']):
         visible_reply = entry[1]
         if visible_reply.startswith('<audio'):
@@ -65,7 +66,8 @@ def toggle_text_in_history(name1, name2):
                 shared.history['visible'][i] = [shared.history['visible'][i][0], f"{visible_reply.split('</audio>')[0]}</audio>\n\n{reply}"]
             else:
                 shared.history['visible'][i] = [shared.history['visible'][i][0], f"{visible_reply.split('</audio>')[0]}</audio>"]
-    return chat.generate_chat_output(shared.history['visible'], name1, name2, shared.character)
+    return chat_html_wrapper(shared.history['visible'], name1, name2, mode)
+
 
 def input_modifier(string):
     """
@@ -81,6 +83,7 @@ def input_modifier(string):
     shared.args.no_stream = True  # Disable streaming cause otherwise the audio output will stutter and begin anew every time the message is being updated
     return string
 
+
 def output_modifier(string):
     """
     This function is applied to the model outputs.
@@ -98,11 +101,7 @@ def output_modifier(string):
         return string
 
     original_string = string
-    string = remove_surrounded_chars(string)
-    string = string.replace('"', '')
-    string = string.replace('“', '')
-    string = string.replace('\n', ' ')
-    string = string.strip()
+    string = tts_preprocessor.preprocess(string)
 
     if string == '':
         string = '*Empty reply, try regenerating*'
@@ -121,6 +120,7 @@ def output_modifier(string):
     shared.args.no_stream = streaming_state  # restore the streaming option to the previous value
     return string
 
+
 def bot_prefix_modifier(string):
     """
     This function is only applied in chat mode. It modifies
@@ -130,33 +130,37 @@ def bot_prefix_modifier(string):
 
     return string
 
+
 def ui():
     # Gradio elements
     with gr.Accordion("Silero TTS"):
         with gr.Row():
             activate = gr.Checkbox(value=params['activate'], label='Activate TTS')
             autoplay = gr.Checkbox(value=params['autoplay'], label='Play TTS automatically')
+
         show_text = gr.Checkbox(value=params['show_text'], label='Show message text under audio player')
         voice = gr.Dropdown(value=params['speaker'], choices=voices_by_gender, label='TTS voice')
         with gr.Row():
             v_pitch = gr.Dropdown(value=params['voice_pitch'], choices=voice_pitches, label='Voice pitch')
             v_speed = gr.Dropdown(value=params['voice_speed'], choices=voice_speeds, label='Voice speed')
+
         with gr.Row():
             convert = gr.Button('Permanently replace audios with the message texts')
             convert_cancel = gr.Button('Cancel', visible=False)
             convert_confirm = gr.Button('Confirm (cannot be undone)', variant="stop", visible=False)
 
+
     # Convert history with confirmation
     convert_arr = [convert_confirm, convert, convert_cancel]
     convert.click(lambda: [gr.update(visible=True), gr.update(visible=False), gr.update(visible=True)], None, convert_arr)
     convert_confirm.click(lambda: [gr.update(visible=False), gr.update(visible=True), gr.update(visible=False)], None, convert_arr)
-    convert_confirm.click(remove_tts_from_history, [shared.gradio['name1'], shared.gradio['name2']], shared.gradio['display'])
+    convert_confirm.click(remove_tts_from_history, [shared.gradio[k] for k in ['name1', 'name2', 'Chat mode']], shared.gradio['display'])
     convert_confirm.click(lambda: chat.save_history(timestamp=False), [], [], show_progress=False)
     convert_cancel.click(lambda: [gr.update(visible=False), gr.update(visible=True), gr.update(visible=False)], None, convert_arr)
 
     # Toggle message text in history
     show_text.change(lambda x: params.update({"show_text": x}), show_text, None)
-    show_text.change(toggle_text_in_history, [shared.gradio['name1'], shared.gradio['name2']], shared.gradio['display'])
+    show_text.change(toggle_text_in_history, [shared.gradio[k] for k in ['name1', 'name2', 'Chat mode']], shared.gradio['display'])
     show_text.change(lambda: chat.save_history(timestamp=False), [], [], show_progress=False)
 
     # Event functions to update the parameters in the backend

extensions/silero_tts/test_tts.py

@@ -0,0 +1,81 @@
+import time
+from pathlib import Path
+
+import torch
+
+import tts_preprocessor
+
+
+torch._C._jit_set_profiling_mode(False)
+
+
+params = {
+    'activate': True,
+    'speaker': 'en_49',
+    'language': 'en',
+    'model_id': 'v3_en',
+    'sample_rate': 48000,
+    'device': 'cpu',
+    'show_text': True,
+    'autoplay': True,
+    'voice_pitch': 'medium',
+    'voice_speed': 'medium',
+}
+
+current_params = params.copy()
+voices_by_gender = ['en_99', 'en_45', 'en_18', 'en_117', 'en_49', 'en_51', 'en_68', 'en_0', 'en_26', 'en_56', 'en_74', 'en_5', 'en_38', 'en_53', 'en_21', 'en_37', 'en_107', 'en_10', 'en_82', 'en_16', 'en_41', 'en_12', 'en_67', 'en_61', 'en_14', 'en_11', 'en_39', 'en_52', 'en_24', 'en_97', 'en_28', 'en_72', 'en_94', 'en_36', 'en_4', 'en_43', 'en_88', 'en_25', 'en_65', 'en_6', 'en_44', 'en_75', 'en_91', 'en_60', 'en_109', 'en_85', 'en_101', 'en_108', 'en_50', 'en_96', 'en_64', 'en_92', 'en_76', 'en_33', 'en_116', 'en_48', 'en_98', 'en_86', 'en_62', 'en_54', 'en_95', 'en_55', 'en_111', 'en_3', 'en_83', 'en_8', 'en_47', 'en_59', 'en_1', 'en_2', 'en_7', 'en_9', 'en_13', 'en_15', 'en_17', 'en_19', 'en_20', 'en_22', 'en_23', 'en_27', 'en_29', 'en_30', 'en_31', 'en_32', 'en_34', 'en_35', 'en_40', 'en_42', 'en_46', 'en_57', 'en_58', 'en_63', 'en_66', 'en_69', 'en_70', 'en_71', 'en_73', 'en_77', 'en_78', 'en_79', 'en_80', 'en_81', 'en_84', 'en_87', 'en_89', 'en_90', 'en_93', 'en_100', 'en_102', 'en_103', 'en_104', 'en_105', 'en_106', 'en_110', 'en_112', 'en_113', 'en_114', 'en_115']
+voice_pitches = ['x-low', 'low', 'medium', 'high', 'x-high']
+voice_speeds = ['x-slow', 'slow', 'medium', 'fast', 'x-fast']
+
+# Used for making text xml compatible, needed for voice pitch and speed control
+table = str.maketrans({
+    "<": "&lt;",
+    ">": "&gt;",
+    "&": "&amp;",
+    "'": "&apos;",
+    '"': "&quot;",
+})
+
+
+def xmlesc(txt):
+    return txt.translate(table)
+
+
+def load_model():
+    model, example_text = torch.hub.load(repo_or_dir='snakers4/silero-models', model='silero_tts', language=params['language'], speaker=params['model_id'])
+    model.to(params['device'])
+    return model
+model = load_model()
+
+
+def output_modifier(string):
+    """
+    This function is applied to the model outputs.
+    """
+
+    global model, current_params
+
+    original_string = string
+    string = tts_preprocessor.preprocess(string)
+    processed_string = string
+
+    if string == '':
+        string = '*Empty reply, try regenerating*'
+    else:
+        output_file = Path(f'extensions/silero_tts/outputs/test_{int(time.time())}.wav')
+        prosody = '<prosody rate="{}" pitch="{}">'.format(params['voice_speed'], params['voice_pitch'])
+        silero_input = f'<speak>{prosody}{xmlesc(string)}</prosody></speak>'
+        model.save_wav(ssml_text=silero_input, speaker=params['speaker'], sample_rate=int(params['sample_rate']), audio_path=str(output_file))
+
+        autoplay = 'autoplay' if params['autoplay'] else ''
+        string = f'<audio src="file/{output_file.as_posix()}" controls {autoplay}></audio>'
+
+        if params['show_text']:
+            string += f'\n\n{original_string}\n\nProcessed:\n{processed_string}'
+
+    print(string)
+
+
+if __name__ == '__main__':
+    import sys
+    output_modifier(sys.argv[1])

extensions/silero_tts/tts_preprocessor.py

@@ -0,0 +1,177 @@
+import re
+
+from num2words import num2words
+
+# punctuation = r'[\s,.?!/)"\'\]>]“”'
+punctuation = r'[\s,.?!/)"\'\]>]'
+alphabet_map = {
+    "A": " Ei ",
+    "B": " Bee ",
+    "C": " See ",
+    "D": " Dee ",
+    "E": " Eee ",
+    "F": " Eff ",
+    "G": " Jee ",
+    "H": " Eich ",
+    "I": " Eye ",
+    "J": " Jay ",
+    "K": " Kay ",
+    "L": " El ",
+    "M": " Emm ",
+    "N": " Enn ",
+    "O": " Ohh ",
+    "P": " Pee ",
+    "Q": " Queue ",
+    "R": " Are ",
+    "S": " Ess ",
+    "T": " Tee ",
+    "U": " You ",
+    "V": " Vee ",
+    "W": " Double You ",
+    "X": " Ex ",
+    "Y": " Why ",
+    "Z": " Zed "  # Zed is weird, as I (da3dsoul) am American, but most of the voice models sound British, so it matches
+}
+
+
+def preprocess(string):
+    # the order for some of these matter
+    # For example, you need to remove the commas in numbers before expanding them
+    string = remove_surrounded_chars(string)
+    string = string.replace('"', '')
+    string = string.replace('“', '')
+    string = string.replace('\n', ' ')
+    string = convert_num_locale(string)
+    string = replace_negative(string)
+    string = replace_roman(string)
+    string = hyphen_range_to(string)
+    string = num_to_words(string)
+
+    # TODO Try to use a ML predictor to expand abbreviations. It's hard, dependent on context, and whether to actually
+    # try to say the abbreviation or spell it out as I've done below is not agreed upon
+
+    # For now, expand abbreviations to pronunciations
+    # replace_abbreviations adds a lot of unnecessary whitespace to ensure separation
+    string = replace_abbreviations(string)
+
+    # cleanup whitespaces
+    # remove whitespace before punctuation
+    string = re.sub(rf'\s+({punctuation})', r'\1', string)
+    string = string.strip()
+    # compact whitespace
+    string = ' '.join(string.split())
+
+    return string
+
+
+def remove_surrounded_chars(string):
+    # this expression matches to 'as few symbols as possible (0 upwards) between any asterisks' OR
+    # 'as few symbols as possible (0 upwards) between an asterisk and the end of the string'
+    return re.sub(r'\*[^*]*?(\*|$)', '', string)
+
+
+def replace_negative(string):
+    # handles situations like -5. -5 would become negative 5, which would then be expanded to negative five
+    return re.sub(rf'(\s)(-)(\d+)({punctuation})', r'\1negative \3\4', string)
+
+
+def replace_roman(string):
+    # find a string of roman numerals.
+    # Only 2 or more, to avoid capturing I and single character abbreviations, like names
+    pattern = re.compile(rf'\s[IVXLCDM]{{2,}}{punctuation}')
+    result = string
+    while True:
+        match = pattern.search(result)
+        if match is None:
+            break
+
+        start = match.start()
+        end = match.end()
+        result = result[0:start + 1] + str(roman_to_int(result[start + 1:end - 1])) + result[end - 1:len(result)]
+
+    return result
+
+
+def roman_to_int(s):
+    rom_val = {'I': 1, 'V': 5, 'X': 10, 'L': 50, 'C': 100, 'D': 500, 'M': 1000}
+    int_val = 0
+    for i in range(len(s)):
+        if i > 0 and rom_val[s[i]] > rom_val[s[i - 1]]:
+            int_val += rom_val[s[i]] - 2 * rom_val[s[i - 1]]
+        else:
+            int_val += rom_val[s[i]]
+    return int_val
+
+
+def hyphen_range_to(text):
+    pattern = re.compile(r'(\d+)[-–](\d+)')
+    result = pattern.sub(lambda x: x.group(1) + ' to ' + x.group(2), text)
+    return result
+
+
+def num_to_words(text):
+    # 1000 or 10.23
+    pattern = re.compile(r'\d+\.\d+|\d+')
+    result = pattern.sub(lambda x: num2words(float(x.group())), text)
+    return result
+
+
+def replace_abbreviations(string):
+    # abbreviations 1 to 4 characters long. It will get things like A and I, but those are pronounced with their letter
+    pattern = re.compile(rf'(^|[\s("\'\[<])([A-Z]{{1,4}})({punctuation}|$)')
+    result = string
+    while True:
+        match = pattern.search(result)
+        if match is None:
+            break
+
+        start = match.start()
+        end = match.end()
+        result = result[0:start] + replace_abbreviation(result[start:end]) + result[end:len(result)]
+
+    return result
+
+
+def replace_abbreviation(string):
+    result = ""
+    for char in string:
+        result = match_mapping(char, result)
+
+    return result
+
+
+def match_mapping(char, result):
+    for mapping in alphabet_map.keys():
+        if char == mapping:
+            return result + alphabet_map[char]
+
+    return result + char
+
+
+def convert_num_locale(text):
+    # This detects locale and converts it to American without comma separators
+    pattern = re.compile(r'(?:\s|^)\d{1,3}(?:\.\d{3})*(?:,\d+)?(?:\s|$)')
+    result = text
+    while True:
+        match = pattern.search(result)
+        if match is None:
+            break
+
+        start = match.start()
+        end = match.end()
+        result = result[0:start] + result[start:end].replace('.', '').replace(',', '.') + result[end:len(result)]
+
+    # removes comma separators from existing American numbers
+    pattern = re.compile(r'(\d),(\d)')
+    result = pattern.sub(r'\1\2', result)
+
+    return result
+
+
+def __main__(args):
+    print(preprocess(args[1]))
+
+
+if __name__ == "__main__":
+    import sys
+    __main__(sys.argv)

modules/GPTQ_loader.py

@@ -17,9 +17,11 @@ from quant import make_quant
 
 
 def _load_quant(model, checkpoint, wbits, groupsize=-1, faster_kernel=False, exclude_layers=['lm_head'], kernel_switch_threshold=128):
-    config = AutoConfig.from_pretrained(model)
+
     def noop(*args, **kwargs):
         pass
+
+    config = AutoConfig.from_pretrained(model)
     torch.nn.init.kaiming_uniform_ = noop
     torch.nn.init.uniform_ = noop
     torch.nn.init.normal_ = noop
@@ -64,6 +66,7 @@ def _load_quant(model, checkpoint, wbits, groupsize=-1, faster_kernel=False, exc
 
     return model
 
+
 def load_quantized(model_name):
     if not shared.args.model_type:
         # Try to determine model type from model name

modules/LoRA.py

@@ -13,6 +13,7 @@ def reload_model():
     clear_torch_cache()
     shared.model, shared.tokenizer = load_model(shared.model_name)
 
+
 def add_lora_to_model(lora_name):
 
     # If a LoRA had been previously loaded, or if we want

modules/RWKV.py

@@ -54,6 +54,7 @@ class RWKVModel:
                 reply += token
                 yield reply
 
+
 class RWKVTokenizer:
     def __init__(self):
         pass

modules/api.py

@@ -28,6 +28,7 @@ def generate_reply_wrapper(string):
     for i in generate_reply(params[0], generate_params):
         yield i
 
+
 def create_apis():
     t1 = gr.Textbox(visible=False)
     t2 = gr.Textbox(visible=False)

modules/callbacks.py

@@ -30,6 +30,7 @@ class _SentinelTokenStoppingCriteria(transformers.StoppingCriteria):
                         return True
         return False
 
+
 class Stream(transformers.StoppingCriteria):
     def __init__(self, callback_func=None):
         self.callback_func = callback_func
@@ -39,6 +40,7 @@ class Stream(transformers.StoppingCriteria):
             self.callback_func(input_ids[0])
         return False
 
+
 class Iteratorize:
 
     """
@@ -96,6 +98,7 @@ class Iteratorize:
         self.stop_now = True
         clear_torch_cache()
 
+
 def clear_torch_cache():
     gc.collect()
     if not shared.args.cpu:

modules/chat.py

@@ -23,7 +23,6 @@ def generate_chat_prompt(user_input, max_new_tokens, name1, name2, context, chat
     end_of_turn = kwargs['end_of_turn'] if 'end_of_turn' in kwargs else ''
     impersonate = kwargs['impersonate'] if 'impersonate' in kwargs else False
     also_return_rows = kwargs['also_return_rows'] if 'also_return_rows' in kwargs else False
-
     rows = [f"{context.strip()}\n"]
 
     # Finding the maximum prompt size
@@ -68,6 +67,7 @@ def generate_chat_prompt(user_input, max_new_tokens, name1, name2, context, chat
     else:
         return prompt
 
+
 def extract_message_from_reply(reply, name1, name2, stop_at_newline):
     next_character_found = False
 
@@ -98,6 +98,7 @@ def extract_message_from_reply(reply, name1, name2, stop_at_newline):
     reply = fix_newlines(reply)
     return reply, next_character_found
 
+
 def chatbot_wrapper(text, generate_state, name1, name2, context, mode, end_of_turn, regenerate=False):
     if mode == 'instruct':
         stopping_strings = [f"\n{name1}", f"\n{name2}"]
@@ -113,7 +114,7 @@ def chatbot_wrapper(text, generate_state, name1, name2, context, mode, end_of_tu
     visible_text = None
     custom_generate_chat_prompt = None
     for extension, _ in extensions_module.iterator():
-        if hasattr(extension, 'input_hijack') and extension.input_hijack['state'] == True:
+        if hasattr(extension, 'input_hijack') and extension.input_hijack['state']:
             extension.input_hijack['state'] = False
             text, visible_text = extension.input_hijack['value']
         if custom_generate_chat_prompt is None and hasattr(extension, 'custom_generate_chat_prompt'):
@@ -167,6 +168,7 @@ def chatbot_wrapper(text, generate_state, name1, name2, context, mode, end_of_tu
 
     yield shared.history['visible']
 
+
 def impersonate_wrapper(text, generate_state, name1, name2, context, mode, end_of_turn):
     if mode == 'instruct':
         stopping_strings = [f"\n{name1}", f"\n{name2}"]
@@ -197,10 +199,12 @@ def impersonate_wrapper(text, generate_state, name1, name2, context, mode, end_o
 
     yield reply
 
+
 def cai_chatbot_wrapper(text, generate_state, name1, name2, context, mode, end_of_turn):
     for history in chatbot_wrapper(text, generate_state, name1, name2, context, mode, end_of_turn):
         yield chat_html_wrapper(history, name1, name2, mode)
 
+
 def regenerate_wrapper(text, generate_state, name1, name2, context, mode, end_of_turn):
     if (shared.character != 'None' and len(shared.history['visible']) == 1) or len(shared.history['internal']) == 0:
         yield chat_html_wrapper(shared.history['visible'], name1, name2, mode)
@@ -213,6 +217,7 @@ def regenerate_wrapper(text, generate_state, name1, name2, context, mode, end_of
             shared.history['visible'][-1] = [last_visible[0], history[-1][1]]
             yield chat_html_wrapper(shared.history['visible'], name1, name2, mode)
 
+
 def remove_last_message(name1, name2, mode):
     if len(shared.history['visible']) > 0 and shared.history['internal'][-1][0] != '<|BEGIN-VISIBLE-CHAT|>':
         last = shared.history['visible'].pop()
@@ -222,12 +227,14 @@ def remove_last_message(name1, name2, mode):
 
     return chat_html_wrapper(shared.history['visible'], name1, name2, mode), last[0]
 
+
 def send_last_reply_to_input():
     if len(shared.history['internal']) > 0:
         return shared.history['internal'][-1][1]
     else:
         return ''
 
+
 def replace_last_reply(text, name1, name2, mode):
     if len(shared.history['visible']) > 0:
         shared.history['visible'][-1][1] = text
@@ -235,9 +242,11 @@ def replace_last_reply(text, name1, name2, mode):
 
     return chat_html_wrapper(shared.history['visible'], name1, name2, mode)
 
+
 def clear_html():
     return chat_html_wrapper([], "", "")
 
+
 def clear_chat_log(name1, name2, greeting, mode):
     shared.history['visible'] = []
     shared.history['internal'] = []
@@ -248,9 +257,11 @@ def clear_chat_log(name1, name2, greeting, mode):
 
     return chat_html_wrapper(shared.history['visible'], name1, name2, mode)
 
+
 def redraw_html(name1, name2, mode):
     return chat_html_wrapper(shared.history['visible'], name1, name2, mode)
 
+
 def tokenize_dialogue(dialogue, name1, name2, mode):
     history = []
 
@@ -288,6 +299,7 @@ def tokenize_dialogue(dialogue, name1, name2, mode):
 
     return history
 
+
 def save_history(timestamp=True):
     if timestamp:
         fname = f"{shared.character}_{datetime.now().strftime('%Y%m%d-%H%M%S')}.json"
@@ -299,6 +311,7 @@ def save_history(timestamp=True):
         f.write(json.dumps({'data': shared.history['internal'], 'data_visible': shared.history['visible']}, indent=2))
     return Path(f'logs/{fname}')
 
+
 def load_history(file, name1, name2):
     file = file.decode('utf-8')
     try:
@@ -323,10 +336,12 @@ def load_history(file, name1, name2):
         shared.history['internal'] = tokenize_dialogue(file, name1, name2)
         shared.history['visible'] = copy.deepcopy(shared.history['internal'])
 
+
 def replace_character_names(text, name1, name2):
     text = text.replace('{{user}}', name1).replace('{{char}}', name2)
     return text.replace('<USER>', name1).replace('<BOT>', name2)
 
+
 def build_pygmalion_style_context(data):
     context = ""
     if 'char_persona' in data and data['char_persona'] != '':
@@ -336,6 +351,7 @@ def build_pygmalion_style_context(data):
     context = f"{context.strip()}\n<START>\n"
     return context
 
+
 def generate_pfp_cache(character):
     cache_folder = Path("cache")
     if not cache_folder.exists():
@@ -348,6 +364,7 @@ def generate_pfp_cache(character):
             return img
     return None
 
+
 def load_character(character, name1, name2, mode):
     shared.character = character
     shared.history['internal'] = []
@@ -404,9 +421,11 @@ def load_character(character, name1, name2, mode):
 
     return name1, name2, picture, greeting, context, end_of_turn, chat_html_wrapper(shared.history['visible'], name1, name2, mode, reset_cache=True)
 
+
 def load_default_history(name1, name2):
     load_character("None", name1, name2, "chat")
 
+
 def upload_character(json_file, img, tavern=False):
     json_file = json_file if type(json_file) == str else json_file.decode('utf-8')
     data = json.loads(json_file)
@@ -425,6 +444,7 @@ def upload_character(json_file, img, tavern=False):
     print(f'New character saved to "characters/{outfile_name}.json".')
     return outfile_name
 
+
 def upload_tavern_character(img, name1, name2):
     _img = Image.open(io.BytesIO(img))
     _img.getexif()
@@ -433,12 +453,13 @@ def upload_tavern_character(img, name1, name2):
     _json = {"char_name": _json['name'], "char_persona": _json['description'], "char_greeting": _json["first_mes"], "example_dialogue": _json['mes_example'], "world_scenario": _json['scenario']}
     return upload_character(json.dumps(_json), img, tavern=True)
 
+
 def upload_your_profile_picture(img, name1, name2, mode):
     cache_folder = Path("cache")
     if not cache_folder.exists():
         cache_folder.mkdir()
 
-    if img == None:
+    if img is None:
         if Path("cache/pfp_me.png").exists():
             Path("cache/pfp_me.png").unlink()
     else:

modules/extensions.py

@@ -9,6 +9,7 @@ state = {}
 available_extensions = []
 setup_called = set()
 
+
 def load_extensions():
     global state
     for i, name in enumerate(shared.args.extensions):
@@ -23,12 +24,16 @@ def load_extensions():
                 traceback.print_exc()
 
 # This iterator returns the extensions in the order specified in the command-line
+
+
 def iterator():
     for name in sorted(state, key=lambda x: state[x][1]):
         if state[name][0] == True:
             yield eval(f"extensions.{name}.script"), name
 
 # Extension functions that map string -> string
+
+
 def apply_extensions(text, typ):
     for extension, _ in iterator():
         if typ == "input" and hasattr(extension, "input_modifier"):
@@ -39,6 +44,7 @@ def apply_extensions(text, typ):
             text = extension.bot_prefix_modifier(text)
     return text
 
+
 def create_extensions_block():
     global setup_called
 

modules/html_generator.py

@@ -24,6 +24,7 @@ with open(Path(__file__).resolve().parent / '../css/html_cai_style.css', 'r') as
 with open(Path(__file__).resolve().parent / '../css/html_instruct_style.css', 'r') as f:
     instruct_css = f.read()
 
+
 def fix_newlines(string):
     string = string.replace('\n', '\n\n')
     string = re.sub(r"\n{3,}", "\n\n", string)
@@ -31,6 +32,8 @@ def fix_newlines(string):
     return string
 
 # This could probably be generalized and improved
+
+
 def convert_to_markdown(string):
     string = string.replace('\\begin{code}', '```')
     string = string.replace('\\end{code}', '```')
@@ -40,11 +43,13 @@ def convert_to_markdown(string):
     string = fix_newlines(string)
     return markdown.markdown(string, extensions=['fenced_code'])
 
+
 def generate_basic_html(string):
     string = convert_to_markdown(string)
     string = f'<style>{readable_css}</style><div class="container">{string}</div>'
     return string
 
+
 def process_post(post, c):
     t = post.split('\n')
     number = t[0].split(' ')[1]
@@ -59,6 +64,7 @@ def process_post(post, c):
     src = f'<span class="name">Anonymous </span> <span class="number">No.{number}</span>\n{src}'
     return src
 
+
 def generate_4chan_html(f):
     posts = []
     post = ''
@@ -98,6 +104,7 @@ def generate_4chan_html(f):
 
     return output
 
+
 def make_thumbnail(image):
     image = image.resize((350, round(image.size[1] / image.size[0] * 350)), Image.Resampling.LANCZOS)
     if image.size[1] > 470:
@@ -105,6 +112,7 @@ def make_thumbnail(image):
 
     return image
 
+
 def get_image_cache(path):
     cache_folder = Path("cache")
     if not cache_folder.exists():
@@ -119,6 +127,7 @@ def get_image_cache(path):
 
     return image_cache[path][1]
 
+
 def generate_instruct_html(history):
     output = f'<style>{instruct_css}</style><div class="chat" id="chat">'
     for i, _row in enumerate(history[::-1]):
@@ -151,6 +160,7 @@ def generate_instruct_html(history):
 
     return output
 
+
 def generate_cai_chat_html(history, name1, name2, reset_cache=False):
     output = f'<style>{cai_css}</style><div class="chat" id="chat">'
 
@@ -200,9 +210,11 @@ def generate_cai_chat_html(history, name1, name2, reset_cache=False):
     output += "</div>"
     return output
 
+
 def generate_chat_html(history, name1, name2):
     return generate_cai_chat_html(history, name1, name2)
 
+
 def chat_html_wrapper(history, name1, name2, mode, reset_cache=False):
     if mode == "cai-chat":
         return generate_cai_chat_html(history, name1, name2, reset_cache)

modules/llamacpp_model_alternative.py

@@ -6,8 +6,6 @@ Documentation:
 https://abetlen.github.io/llama-cpp-python/
 '''
 
-import multiprocessing
-
 from llama_cpp import Llama
 
 from modules import shared

modules/models.py

@@ -181,6 +181,7 @@ def load_model(model_name):
     print(f"Loaded the model in {(time.time()-t0):.2f} seconds.")
     return model, tokenizer
 
+
 def load_soft_prompt(name):
     if name == 'None':
         shared.soft_prompt = False

modules/shared.py

@@ -61,6 +61,7 @@ settings = {
     }
 }
 
+
 def str2bool(v):
     if isinstance(v, bool):
         return v
@@ -71,6 +72,7 @@ def str2bool(v):
     else:
         raise argparse.ArgumentTypeError('Boolean value expected.')
 
+
 parser = argparse.ArgumentParser(formatter_class=lambda prog: argparse.HelpFormatter(prog, max_help_position=54))
 
 # Basic settings
@@ -145,5 +147,6 @@ if args.cai_chat:
     print("Warning: --cai-chat is deprecated. Use --chat instead.")
     args.chat = True
 
+
 def is_chat():
     return args.chat

modules/text_generation.py

@@ -21,6 +21,7 @@ def get_max_prompt_length(tokens):
         max_length -= shared.soft_prompt_tensor.shape[1]
     return max_length
 
+
 def encode(prompt, tokens_to_generate=0, add_special_tokens=True):
     if any((shared.is_RWKV, shared.is_llamacpp)):
         input_ids = shared.tokenizer.encode(str(prompt))
@@ -44,6 +45,7 @@ def encode(prompt, tokens_to_generate=0, add_special_tokens=True):
         else:
             return input_ids.cuda()
 
+
 def decode(output_ids):
     # Open Assistant relies on special tokens like <|endoftext|>
     if re.match('.*(oasst|galactica)-*', shared.model_name.lower()):
@@ -53,6 +55,7 @@ def decode(output_ids):
         reply = reply.replace(r'<|endoftext|>', '')
         return reply
 
+
 def generate_softprompt_input_tensors(input_ids):
     inputs_embeds = shared.model.transformer.wte(input_ids)
     inputs_embeds = torch.cat((shared.soft_prompt_tensor, inputs_embeds), dim=1)
@@ -61,6 +64,8 @@ def generate_softprompt_input_tensors(input_ids):
     return inputs_embeds, filler_input_ids
 
 # Removes empty replies from gpt4chan outputs
+
+
 def fix_gpt4chan(s):
     for i in range(10):
         s = re.sub("--- [0-9]*\n>>[0-9]*\n---", "---", s)
@@ -69,6 +74,8 @@ def fix_gpt4chan(s):
     return s
 
 # Fix the LaTeX equations in galactica
+
+
 def fix_galactica(s):
     s = s.replace(r'\[', r'$')
     s = s.replace(r'\]', r'$')
@@ -79,6 +86,7 @@ def fix_galactica(s):
     s = re.sub(r"\n{3,}", "\n\n", s)
     return s
 
+
 def formatted_outputs(reply, model_name):
     if not shared.is_chat():
         if 'galactica' in model_name.lower():
@@ -92,20 +100,24 @@ def formatted_outputs(reply, model_name):
     else:
         return reply
 
+
 def clear_torch_cache():
     gc.collect()
     if not shared.args.cpu:
         torch.cuda.empty_cache()
 
+
 def set_manual_seed(seed):
     if seed != -1:
         torch.manual_seed(seed)
         if torch.cuda.is_available():
             torch.cuda.manual_seed_all(seed)
 
+
 def stop_everything_event():
     shared.stop_everything = True
 
+
 def generate_reply(question, generate_state, eos_token=None, stopping_strings=[]):
     clear_torch_cache()
     set_manual_seed(generate_state['seed'])

modules/training.py

@@ -19,9 +19,11 @@ CURRENT_STEPS = 0
 MAX_STEPS = 0
 CURRENT_GRADIENT_ACCUM = 1
 
+
 def get_dataset(path: str, ext: str):
     return ['None'] + sorted(set([k.stem for k in Path(path).glob(f'*.{ext}') if k.stem != 'put-trainer-datasets-here']), key=str.lower)
 
+
 def create_train_interface():
     with gr.Tab('Train LoRA', elem_id='lora-train-tab'):
         lora_name = gr.Textbox(label="Name", info="The name of your new LoRA file")
@@ -67,10 +69,12 @@ def create_train_interface():
                                       cutoff_len, dataset, eval_dataset, format, raw_text_file, overlap_len, newline_favor_len], [output])
         stop_button.click(do_interrupt, [], [], cancels=[], queue=False)
 
+
 def do_interrupt():
     global WANT_INTERRUPT
     WANT_INTERRUPT = True
 
+
 class Callbacks(transformers.TrainerCallback):
     def on_step_begin(self, args: transformers.TrainingArguments, state: transformers.TrainerState, control: transformers.TrainerControl, **kwargs):
         global CURRENT_STEPS, MAX_STEPS
@@ -79,6 +83,7 @@ class Callbacks(transformers.TrainerCallback):
         if WANT_INTERRUPT:
             control.should_epoch_stop = True
             control.should_training_stop = True
+
     def on_substep_end(self, args: transformers.TrainingArguments, state: transformers.TrainerState, control: transformers.TrainerControl, **kwargs):
         global CURRENT_STEPS
         CURRENT_STEPS += 1
@@ -86,6 +91,7 @@ class Callbacks(transformers.TrainerCallback):
             control.should_epoch_stop = True
             control.should_training_stop = True
 
+
 def clean_path(base_path: str, path: str):
     """"Strips unusual symbols and forcibly builds a path as relative to the intended directory."""
     # TODO: Probably could do with a security audit to guarantee there's no ways this can be bypassed to target an unwanted path.
@@ -95,6 +101,7 @@ def clean_path(base_path: str, path: str):
         return path
     return f'{Path(base_path).absolute()}/{path}'
 
+
 def do_train(lora_name: str, micro_batch_size: int, batch_size: int, epochs: int, learning_rate: str, lora_rank: int, lora_alpha: int, lora_dropout: float,
              cutoff_len: int, dataset: str, eval_dataset: str, format: str, raw_text_file: str, overlap_len: int, newline_favor_len: int):
     global WANT_INTERRUPT, CURRENT_STEPS, MAX_STEPS, CURRENT_GRADIENT_ACCUM
@@ -302,10 +309,12 @@ def do_train(lora_name: str, micro_batch_size: int, batch_size: int, epochs: int
         print("Training complete!")
         yield f"Done! LoRA saved to `{lora_name}`"
 
+
 def split_chunks(arr, step):
     for i in range(0, len(arr), step):
         yield arr[i:i + step]
 
+
 def cut_chunk_for_newline(chunk: str, max_length: int):
     if '\n' not in chunk:
         return chunk
@@ -319,6 +328,7 @@ def cut_chunk_for_newline(chunk: str, max_length: int):
         chunk = chunk[:last_newline]
     return chunk
 
+
 def format_time(seconds: float):
     if seconds < 120:
         return f"`{seconds:.0f}` seconds"

modules/ui.py

@@ -13,6 +13,7 @@ with open(Path(__file__).resolve().parent / '../css/main.js', 'r') as f:
 with open(Path(__file__).resolve().parent / '../css/chat.js', 'r') as f:
     chat_js = f.read()
 
+
 class ToolButton(gr.Button, gr.components.FormComponent):
     """Small button with single emoji as text, fits inside gradio forms"""
 
@@ -22,6 +23,7 @@ class ToolButton(gr.Button, gr.components.FormComponent):
     def get_block_name(self):
         return "button"
 
+
 def create_refresh_button(refresh_component, refresh_method, refreshed_args, elem_id):
     def refresh():
         refresh_method()

server.py

@@ -34,15 +34,18 @@ if settings_file is not None:
     for item in new_settings:
         shared.settings[item] = new_settings[item]
 
+
 def get_available_models():
     if shared.args.flexgen:
         return sorted([re.sub('-np$', '', item.name) for item in list(Path(f'{shared.args.model_dir}/').glob('*')) if item.name.endswith('-np')], key=str.lower)
     else:
         return sorted([re.sub('.pth$', '', item.name) for item in list(Path(f'{shared.args.model_dir}/').glob('*')) if not item.name.endswith(('.txt', '-np', '.pt', '.json'))], key=str.lower)
 
+
 def get_available_presets():
     return sorted(set((k.stem for k in Path('presets').glob('*.txt'))), key=str.lower)
 
+
 def get_available_prompts():
     prompts = []
     prompts += sorted(set((k.stem for k in Path('prompts').glob('[0-9]*.txt'))), key=str.lower, reverse=True)
@@ -50,10 +53,12 @@ def get_available_prompts():
     prompts += ['None']
     return prompts
 
+
 def get_available_characters():
     paths = (x for x in Path('characters').iterdir() if x.suffix in ('.json', '.yaml', '.yml'))
     return ['None'] + sorted(set((k.stem for k in paths if k.stem != "instruction-following")), key=str.lower)
 
+
 def get_available_instruction_templates():
     path = "characters/instruction-following"
     paths = []
@@ -61,19 +66,24 @@ def get_available_instruction_templates():
         paths = (x for x in Path(path).iterdir() if x.suffix in ('.json', '.yaml', '.yml'))
     return ['None'] + sorted(set((k.stem for k in paths)), key=str.lower)
 
+
 def get_available_extensions():
     return sorted(set(map(lambda x: x.parts[1], Path('extensions').glob('*/script.py'))), key=str.lower)
 
+
 def get_available_softprompts():
     return ['None'] + sorted(set((k.stem for k in Path('softprompts').glob('*.zip'))), key=str.lower)
 
+
 def get_available_loras():
     return ['None'] + sorted([item.name for item in list(Path(shared.args.lora_dir).glob('*')) if not item.name.endswith(('.txt', '-np', '.pt', '.json'))], key=str.lower)
 
+
 def unload_model():
     shared.model = shared.tokenizer = None
     clear_torch_cache()
 
+
 def load_model_wrapper(selected_model):
     if selected_model != shared.model_name:
         shared.model_name = selected_model
@@ -84,10 +94,12 @@ def load_model_wrapper(selected_model):
 
     return selected_model
 
+
 def load_lora_wrapper(selected_lora):
     add_lora_to_model(selected_lora)
     return selected_lora
 
+
 def load_preset_values(preset_menu, state, return_dict=False):
     generate_params = {
         'do_sample': True,
@@ -118,6 +130,7 @@ def load_preset_values(preset_menu, state, return_dict=False):
         state.update(generate_params)
         return state, *[generate_params[k] for k in ['do_sample', 'temperature', 'top_p', 'typical_p', 'repetition_penalty', 'encoder_repetition_penalty', 'top_k', 'min_length', 'no_repeat_ngram_size', 'num_beams', 'penalty_alpha', 'length_penalty', 'early_stopping']]
 
+
 def upload_soft_prompt(file):
     with zipfile.ZipFile(io.BytesIO(file)) as zf:
         zf.extract('meta.json')
@@ -130,12 +143,14 @@ def upload_soft_prompt(file):
 
     return name
 
+
 def save_prompt(text):
     fname = f"{datetime.now().strftime('%Y-%m-%d-%H%M%S')}.txt"
     with open(Path(f'prompts/{fname}'), 'w', encoding='utf-8') as f:
         f.write(text)
     return f"Saved to prompts/{fname}"
 
+
 def load_prompt(fname):
     if fname in ['None', '']:
         return ''
@@ -146,6 +161,7 @@ def load_prompt(fname):
                 text = text[:-1]
             return text
 
+
 def create_prompt_menus():
     with gr.Row():
         with gr.Column():
@@ -161,6 +177,7 @@ def create_prompt_menus():
     shared.gradio['prompt_menu'].change(load_prompt, [shared.gradio['prompt_menu']], [shared.gradio['textbox']], show_progress=False)
     shared.gradio['save_prompt'].click(save_prompt, [shared.gradio['textbox']], [shared.gradio['status']], show_progress=False)
 
+
 def create_model_menus():
     with gr.Row():
         with gr.Column():
@@ -175,6 +192,7 @@ def create_model_menus():
     shared.gradio['model_menu'].change(load_model_wrapper, shared.gradio['model_menu'], shared.gradio['model_menu'], show_progress=True)
     shared.gradio['lora_menu'].change(load_lora_wrapper, shared.gradio['lora_menu'], shared.gradio['lora_menu'], show_progress=True)
 
+
 def create_settings_menus(default_preset):
     generate_params = load_preset_values(default_preset if not shared.args.flexgen else 'Naive', {}, return_dict=True)
     for k in ['max_new_tokens', 'seed', 'stop_at_newline', 'chat_prompt_size', 'chat_generation_attempts']:
@@ -209,7 +227,6 @@ def create_settings_menus(default_preset):
             with gr.Box():
                 gr.Markdown('Contrastive search')
                 shared.gradio['penalty_alpha'] = gr.Slider(0, 5, value=generate_params['penalty_alpha'], label='penalty_alpha')
-
             with gr.Box():
                 gr.Markdown('Beam search (uses a lot of VRAM)')
                 with gr.Row():
@@ -219,7 +236,6 @@ def create_settings_menus(default_preset):
                         shared.gradio['length_penalty'] = gr.Slider(-5, 5, value=generate_params['length_penalty'], label='length_penalty')
                 shared.gradio['early_stopping'] = gr.Checkbox(value=generate_params['early_stopping'], label='early_stopping')
 
-
     with gr.Accordion('Soft prompt', open=False):
         with gr.Row():
             shared.gradio['softprompts_menu'] = gr.Dropdown(choices=available_softprompts, value='None', label='Soft prompt')
@@ -233,6 +249,7 @@ def create_settings_menus(default_preset):
     shared.gradio['softprompts_menu'].change(load_soft_prompt, shared.gradio['softprompts_menu'], shared.gradio['softprompts_menu'], show_progress=True)
     shared.gradio['upload_softprompt'].upload(upload_soft_prompt, shared.gradio['upload_softprompt'], shared.gradio['softprompts_menu'])
 
+
 def set_interface_arguments(interface_mode, extensions, bool_active):
     modes = ["default", "notebook", "chat", "cai_chat"]
     cmd_list = vars(shared.args)
@@ -251,6 +268,7 @@ def set_interface_arguments(interface_mode, extensions, bool_active):
 
     shared.need_restart = True
 
+
 available_models = get_available_models()
 available_presets = get_available_presets()
 available_characters = get_available_characters()
@@ -299,8 +317,8 @@ else:
     default_text = load_prompt(shared.settings['prompts'][next((k for k in shared.settings['prompts'] if re.match(k.lower(), shared.model_name.lower())), 'default')])
 title = 'Text generation web UI'
 
-def create_interface():
 
+def create_interface():
     gen_events = []
     if shared.args.extensions is not None and len(shared.args.extensions) > 0:
         extensions_module.load_extensions()
@@ -562,6 +580,7 @@ def create_interface():
     else:
         shared.gradio['interface'].launch(prevent_thread_lock=True, share=shared.args.share, server_port=shared.args.listen_port, inbrowser=shared.args.auto_launch, auth=auth)
 
+
 create_interface()
 
 while True: