diff --git a/README.md b/README.md index 9201df13..3c9996aa 100644 --- a/README.md +++ b/README.md @@ -196,7 +196,6 @@ Optionally, you can use the following command-line flags: | `--model-dir MODEL_DIR` | Path to directory with all the models. | | `--lora-dir LORA_DIR` | Path to directory with all the loras. | | `--model-menu` | Show a model menu in the terminal when the web UI is first launched. | -| `--no-stream` | Don't stream the text output in real time. | | `--settings SETTINGS_FILE` | Load the default interface settings from this yaml file. See `settings-template.yaml` for an example. If you create a file called `settings.yaml`, this file will be loaded by default without the need to use the `--settings` flag. | | `--extensions EXTENSIONS [EXTENSIONS ...]` | The list of extensions to load. If you want to load more than one extension, write the names separated by spaces. | | `--verbose` | Print the prompts to the terminal. | diff --git a/modules/chat.py b/modules/chat.py index ffddb700..dad3d8b3 100644 --- a/modules/chat.py +++ b/modules/chat.py @@ -261,7 +261,7 @@ def chatbot_wrapper(text, state, regenerate=False, _continue=False, loading_mess yield output -def impersonate_wrapper(text, start_with, state): +def impersonate_wrapper(text, state): if shared.model_name == 'None' or shared.model is None: logger.error("No model is loaded! Select one in the Model tab.") yield '' @@ -291,15 +291,15 @@ def generate_chat_reply(text, state, regenerate=False, _continue=False, loading_ # Same as above but returns HTML for the UI -def generate_chat_reply_wrapper(text, start_with, state, regenerate=False, _continue=False): - if start_with != '' and not _continue: +def generate_chat_reply_wrapper(text, state, regenerate=False, _continue=False): + if state['start_with'] != '' and not _continue: if regenerate: text, state['history'] = remove_last_message(state['history']) regenerate = False _continue = True send_dummy_message(text, state) - send_dummy_reply(start_with, state) + send_dummy_reply(state['start_with'], state) for i, history in enumerate(generate_chat_reply(text, state, regenerate, _continue, loading_message=True)): yield chat_html_wrapper(history, state['name1'], state['name2'], state['mode'], state['chat_style']), history diff --git a/modules/shared.py b/modules/shared.py index 89b5f0cb..e36e2437 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -29,34 +29,35 @@ session_is_loading = False # UI defaults settings = { 'dark_theme': True, - 'autoload_model': False, + 'start_with': '', + 'mode': 'chat', + 'chat_style': 'TheEncrypted777', + 'character': 'None', + 'prompt-default': 'QA', + 'prompt-notebook': 'QA', + 'preset': 'simple-1', 'max_new_tokens': 200, 'max_new_tokens_min': 1, 'max_new_tokens_max': 4096, - 'auto_max_new_tokens': False, 'seed': -1, 'negative_prompt': '', - 'character': 'None', + 'truncation_length': 2048, + 'truncation_length_min': 0, + 'truncation_length_max': 16384, + 'custom_stopping_strings': '', + 'auto_max_new_tokens': False, + 'ban_eos_token': False, + 'add_bos_token': True, + 'skip_special_tokens': True, + 'stream': True, 'name1': 'You', 'name2': 'Assistant', 'context': 'This is a conversation with your Assistant. It is a computer program designed to help you with various tasks such as answering questions, providing recommendations, and helping with decision making. You can ask it anything you want and it will do its best to give you accurate and relevant information.', 'greeting': '', - 'turn_template': '', - 'custom_stopping_strings': '', - 'add_bos_token': True, - 'ban_eos_token': False, - 'skip_special_tokens': True, - 'truncation_length': 2048, - 'truncation_length_min': 0, - 'truncation_length_max': 16384, - 'mode': 'chat', - 'start_with': '', - 'chat_style': 'TheEncrypted777', 'instruction_template': 'None', 'chat-instruct_command': 'Continue the chat dialogue below. Write a single reply for the character "<|character|>".\n\n<|prompt|>', + 'autoload_model': False, 'default_extensions': ['gallery'], - 'preset': 'simple-1', - 'prompt': 'QA', } @@ -83,7 +84,7 @@ parser.add_argument('--lora', type=str, nargs="+", help='The list of LoRAs to lo parser.add_argument("--model-dir", type=str, default='models/', help="Path to directory with all the models") parser.add_argument("--lora-dir", type=str, default='loras/', help="Path to directory with all the loras") parser.add_argument('--model-menu', action='store_true', help='Show a model menu in the terminal when the web UI is first launched.') -parser.add_argument('--no-stream', action='store_true', help='Don\'t stream the text output in real time.') +parser.add_argument('--no-stream', action='store_true', help='DEPRECATED') parser.add_argument('--settings', type=str, help='Load the default interface settings from this yaml file. See settings-template.yaml for an example. If you create a file called settings.yaml, this file will be loaded by default without the need to use the --settings flag.') parser.add_argument('--extensions', type=str, nargs="+", help='The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.') parser.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.') @@ -181,7 +182,7 @@ args = parser.parse_args() args_defaults = parser.parse_args([]) # Deprecation warnings -for k in ['chat', 'notebook']: +for k in ['chat', 'notebook', 'no_stream']: if getattr(args, k): logger.warning(f'--{k} has been deprecated and will be removed soon. Please remove that flag.') diff --git a/modules/ui.py b/modules/ui.py index a7d7811e..19b9997f 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1,7 +1,9 @@ +import copy from pathlib import Path import gradio as gr import torch +import yaml from modules import shared @@ -119,6 +121,7 @@ def list_interface_input_elements(): # Chat elements elements += [ 'textbox', + 'start_with', 'character_menu', 'history', 'name1', @@ -139,7 +142,9 @@ def list_interface_input_elements(): elements += [ 'textbox-notebook', 'textbox-default', - 'output_textbox' + 'output_textbox', + 'prompt_menu-default', + 'prompt_menu-notebook', ] # Model elements @@ -170,6 +175,24 @@ def apply_interface_values(state, use_persistent=False): return [state[k] if k in state else gr.update() for k in elements] +def save_settings(state, preset, instruction_template, extensions): + output = copy.deepcopy(shared.settings) + exclude = ['name1', 'name2', 'greeting', 'context', 'turn_template'] + for k in state: + if k in shared.settings and k not in exclude: + output[k] = state[k] + + output['preset'] = preset + output['prompt-default'] = state['prompt_menu-default'] + output['prompt-notebook'] = state['prompt_menu-notebook'] + output['character'] = state['character_menu'] + output['instruction_template'] = instruction_template + output['default_extensions'] = extensions + output['seed'] = int(output['seed']) + + return yaml.dump(output, sort_keys=False, width=float("inf")) + + class ToolButton(gr.Button, gr.components.IOComponent): """ Small button with single emoji as text, fits inside gradio forms diff --git a/modules/ui_chat.py b/modules/ui_chat.py index 461cf811..d8179867 100644 --- a/modules/ui_chat.py +++ b/modules/ui_chat.py @@ -10,7 +10,7 @@ from modules.html_generator import chat_html_wrapper from modules.text_generation import stop_everything_event from modules.utils import gradio -inputs = ('Chat input', 'start_with', 'interface_state') +inputs = ('Chat input', 'interface_state') reload_arr = ('history', 'name1', 'name2', 'mode', 'chat_style') clear_arr = ('Clear history-confirm', 'Clear history', 'Clear history-cancel') @@ -82,7 +82,7 @@ def create_chat_settings_ui(): shared.gradio['name1_instruct'] = gr.Textbox(value='', lines=2, label='User string') shared.gradio['name2_instruct'] = gr.Textbox(value='', lines=1, label='Bot string') shared.gradio['context_instruct'] = gr.Textbox(value='', lines=4, label='Context') - shared.gradio['turn_template'] = gr.Textbox(value=shared.settings['turn_template'], lines=1, label='Turn template', info='Used to precisely define the placement of spaces and new line characters in instruction prompts.') + shared.gradio['turn_template'] = gr.Textbox(value='', lines=1, label='Turn template', info='Used to precisely define the placement of spaces and new line characters in instruction prompts.') with gr.Row(): shared.gradio['send_instruction_to_default'] = gr.Button('Send to default', elem_classes=['small-button']) shared.gradio['send_instruction_to_notebook'] = gr.Button('Send to notebook', elem_classes=['small-button']) diff --git a/modules/ui_default.py b/modules/ui_default.py index d26863bc..e4771fb8 100644 --- a/modules/ui_default.py +++ b/modules/ui_default.py @@ -13,13 +13,11 @@ outputs = ('output_textbox', 'html-default') def create_ui(): - default_text = load_prompt(shared.settings['prompt']) - with gr.Tab('Default', elem_id='default-tab'): shared.gradio['last_input-default'] = gr.State('') with gr.Row(): with gr.Column(): - shared.gradio['textbox-default'] = gr.Textbox(value=default_text, elem_classes=['textbox_default', 'add_scrollbar'], lines=27, label='Input') + shared.gradio['textbox-default'] = gr.Textbox(value='', elem_classes=['textbox_default', 'add_scrollbar'], lines=27, label='Input') with gr.Row(): shared.gradio['Generate-default'] = gr.Button('Generate', variant='primary') shared.gradio['Stop-default'] = gr.Button('Stop', elem_id='stop') diff --git a/modules/ui_notebook.py b/modules/ui_notebook.py index 7d6648d2..dba9039a 100644 --- a/modules/ui_notebook.py +++ b/modules/ui_notebook.py @@ -13,14 +13,12 @@ outputs = ('textbox-notebook', 'html-notebook') def create_ui(): - default_text = load_prompt(shared.settings['prompt']) - with gr.Tab('Notebook', elem_id='notebook-tab'): shared.gradio['last_input-notebook'] = gr.State('') with gr.Row(): with gr.Column(scale=4): with gr.Tab('Raw'): - shared.gradio['textbox-notebook'] = gr.Textbox(value=default_text, elem_classes=['textbox', 'add_scrollbar'], lines=27) + shared.gradio['textbox-notebook'] = gr.Textbox(value='', elem_classes=['textbox', 'add_scrollbar'], lines=27) with gr.Tab('Markdown'): shared.gradio['markdown_render-notebook'] = gr.Button('Render') diff --git a/modules/ui_parameters.py b/modules/ui_parameters.py index 235fd0bf..a0f95158 100644 --- a/modules/ui_parameters.py +++ b/modules/ui_parameters.py @@ -121,7 +121,7 @@ def create_ui(default_preset): shared.gradio['add_bos_token'] = gr.Checkbox(value=shared.settings['add_bos_token'], label='Add the bos_token to the beginning of prompts', info='Disabling this can make the replies more creative.') shared.gradio['skip_special_tokens'] = gr.Checkbox(value=shared.settings['skip_special_tokens'], label='Skip special tokens', info='Some specific models need this unset.') - shared.gradio['stream'] = gr.Checkbox(value=not shared.args.no_stream, label='Activate text streaming') + shared.gradio['stream'] = gr.Checkbox(value=shared.settings['stream'], label='Activate text streaming') ui_chat.create_chat_settings_ui() diff --git a/modules/ui_session.py b/modules/ui_session.py index 3d0fdac6..b774a207 100644 --- a/modules/ui_session.py +++ b/modules/ui_session.py @@ -9,8 +9,10 @@ def create_ui(): with gr.Tab("Session", elem_id="session-tab"): with gr.Row(): with gr.Column(): - shared.gradio['reset_interface'] = gr.Button("Apply and restart") - shared.gradio['toggle_dark_mode'] = gr.Button('Toggle 💡') + shared.gradio['reset_interface'] = gr.Button("Apply flags/extensions and restart") + with gr.Row(): + shared.gradio['toggle_dark_mode'] = gr.Button('Toggle 💡') + shared.gradio['save_settings'] = gr.Button('Save UI defaults to settings.yaml') with gr.Row(): with gr.Column(): @@ -37,6 +39,12 @@ def create_ui(): lambda: None, None, None, _js='() => {document.body.innerHTML=\'

Reloading...

\'; setTimeout(function(){location.reload()},2500); return []}') shared.gradio['toggle_dark_mode'].click(lambda: None, None, None, _js='() => {document.getElementsByTagName("body")[0].classList.toggle("dark")}') + shared.gradio['save_settings'].click( + ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then( + ui.save_settings, gradio('interface_state', 'preset_menu', 'instruction_template', 'extensions_menu'), gradio('save_contents')).then( + lambda: './', None, gradio('save_root')).then( + lambda: 'settings.yaml', None, gradio('save_filename')).then( + lambda: gr.update(visible=True), None, gradio('file_saver')) def set_interface_arguments(extensions, bool_active): diff --git a/server.py b/server.py index e86e3338..d90453a0 100644 --- a/server.py +++ b/server.py @@ -71,7 +71,9 @@ def create_interface(): 'loader': shared.args.loader or 'Transformers', 'mode': shared.settings['mode'], 'character_menu': shared.args.character or shared.settings['character'], - 'instruction_template': shared.settings['instruction_template'] + 'instruction_template': shared.settings['instruction_template'], + 'prompt_menu-default': shared.settings['prompt-default'], + 'prompt_menu-notebook': shared.settings['prompt-notebook'], }) if Path("cache/pfp_character.png").exists(): diff --git a/settings-template.yaml b/settings-template.yaml index b1d63c71..11cd1185 100644 --- a/settings-template.yaml +++ b/settings-template.yaml @@ -1,33 +1,34 @@ dark_theme: true -autoload_model: false +start_with: '' +mode: chat +chat_style: TheEncrypted777 +character: None +prompt-default: QA +prompt-notebook: QA +preset: simple-1 max_new_tokens: 200 max_new_tokens_min: 1 max_new_tokens_max: 4096 -auto_max_new_tokens: false seed: -1 negative_prompt: '' -character: None +truncation_length: 2048 +truncation_length_min: 0 +truncation_length_max: 16384 +custom_stopping_strings: '' +auto_max_new_tokens: false +ban_eos_token: false +add_bos_token: true +skip_special_tokens: true +stream: true name1: You name2: Assistant context: This is a conversation with your Assistant. It is a computer program designed to help you with various tasks such as answering questions, providing recommendations, and helping with decision making. You can ask it anything you want and it will do its best to give you accurate and relevant information. greeting: '' -turn_template: '' -custom_stopping_strings: '' -add_bos_token: true -ban_eos_token: false -skip_special_tokens: true -truncation_length: 2048 -truncation_length_min: 0 -truncation_length_max: 16384 -mode: chat -start_with: '' -chat_style: TheEncrypted777 instruction_template: None chat-instruct_command: |- Continue the chat dialogue below. Write a single reply for the character "<|character|>". <|prompt|> +autoload_model: false default_extensions: - gallery -preset: simple-1 -prompt: QA