diff --git a/modules/chat.py b/modules/chat.py index 14f2a4f7..f740db55 100644 --- a/modules/chat.py +++ b/modules/chat.py @@ -1220,6 +1220,45 @@ def load_character(character, name1, name2): return name1, name2, picture, greeting, context +def reset_character_for_ui(state): + """Reset character fields to the currently loaded character's saved values""" + if state['character_menu'] and state['character_menu'] != 'None': + try: + name1, name2, picture, greeting, context = load_character(state['character_menu'], state['name1'], state['name2']) + + state['name2'] = name2 + state['greeting'] = greeting + state['context'] = context + state['character_picture'] = picture # This triggers cache update via generate_pfp_cache + + return state, name2, context, greeting, picture + + except Exception as e: + logger.error(f"Failed to reset character '{state['character_menu']}': {e}") + return clear_character_for_ui(state) + else: + return clear_character_for_ui(state) + + +def clear_character_for_ui(state): + """Clear all character fields and picture cache""" + state['name2'] = shared.settings['name2'] + state['context'] = shared.settings['context'] + state['greeting'] = shared.settings['greeting'] + state['character_picture'] = None + + # Clear the cache files + cache_folder = Path(shared.args.disk_cache_dir) + for cache_file in ['pfp_character.png', 'pfp_character_thumb.png']: + cache_path = Path(f'{cache_folder}/{cache_file}') + if cache_path.exists(): + cache_path.unlink() + + logger.info("Cleared character fields and picture cache") + + return state, state['name2'], state['context'], state['greeting'], None + + def load_instruction_template(template): if template == 'None': return '' @@ -1710,6 +1749,28 @@ def handle_character_menu_change(state): ] +def handle_character_picture_change(picture): + """Update or clear cache when character picture changes""" + cache_folder = Path(shared.args.disk_cache_dir) + if not cache_folder.exists(): + cache_folder.mkdir() + + if picture is not None: + # Save to cache + picture.save(Path(f'{cache_folder}/pfp_character.png'), format='PNG') + thumb = make_thumbnail(picture) + thumb.save(Path(f'{cache_folder}/pfp_character_thumb.png'), format='PNG') + logger.info("Updated character picture cache") + else: + # Remove cache files when picture is cleared + for cache_file in ['pfp_character.png', 'pfp_character_thumb.png']: + cache_path = Path(f'{cache_folder}/{cache_file}') + if cache_path.exists(): + cache_path.unlink() + + logger.info("Cleared character picture cache") + + def handle_mode_change(state): history = load_latest_history(state) histories = find_all_histories_with_first_prompts(state) diff --git a/modules/html_generator.py b/modules/html_generator.py index f90e3b04..eac7d91a 100644 --- a/modules/html_generator.py +++ b/modules/html_generator.py @@ -520,17 +520,23 @@ def generate_instruct_html(history, last_message_only=False): return output +def get_character_image_with_cache_buster(): + """Get character image URL with cache busting based on file modification time""" + cache_path = Path("user_data/cache/pfp_character_thumb.png") + if cache_path.exists(): + mtime = int(cache_path.stat().st_mtime) + return f'' + + return '' + + def generate_cai_chat_html(history, name1, name2, style, character, reset_cache=False, last_message_only=False): if not last_message_only: output = f'
' else: output = "" - # We use ?character and ?time.time() to force the browser to reset caches - img_bot = ( - f'' - if Path("user_data/cache/pfp_character_thumb.png").exists() else '' - ) + img_bot = get_character_image_with_cache_buster() def create_message(role, content, raw_content): """Inner function for CAI-style messages.""" diff --git a/modules/presets.py b/modules/presets.py index cf706605..3eb1f5fc 100644 --- a/modules/presets.py +++ b/modules/presets.py @@ -1,6 +1,5 @@ import functools import pprint -import random from pathlib import Path import yaml @@ -93,68 +92,17 @@ def load_preset_for_ui(name, state): return state, *[generate_params[k] for k in presets_params()] -def random_preset(state): - params_and_values = { - 'remove_tail_tokens': { - 'top_p': [0.5, 0.8, 0.9, 0.95, 0.99], - 'min_p': [0.5, 0.2, 0.1, 0.05, 0.01], - 'top_k': [3, 5, 10, 20, 30, 40], - 'typical_p': [0.2, 0.575, 0.95], - 'tfs': [0.5, 0.8, 0.9, 0.95, 0.99], - 'top_a': [0.5, 0.2, 0.1, 0.05, 0.01], - 'epsilon_cutoff': [1, 3, 5, 7, 9], - 'eta_cutoff': [3, 6, 9, 12, 15, 18], - }, - 'flatten_distribution': { - 'temperature': [0.1, 0.5, 0.7, 0.8, 1, 1.2, 1.5, 2.0, 5.0], - 'dynamic_temperature': [ - [0.1, 1], - [0.1, 1.5], - [0.1, 2], - [0.1, 5], - [0.5, 1], - [0.5, 1.5], - [0.5, 2], - [0.5, 5], - [0.8, 1], - [0.8, 1.5], - [0.8, 2], - [0.8, 5], - [1, 1.5], - [1, 2], - [1, 5] - ], - 'smoothing_factor': [0.2, 0.3, 0.6, 1.2], - }, - 'repetition': { - 'repetition_penalty': [1, 1.05, 1.1, 1.15, 1.20, 1.25], - 'presence_penalty': [0, 0.1, 0.2, 0.4, 0.6, 0.8, 1.0, 2.0], - 'frequency_penalty': [0, 0.1, 0.2, 0.4, 0.6, 0.8, 1.0, 2.0], - }, - 'other': { - 'temperature_last': [True, False], - } - } - - generate_params = default_preset() - for cat in params_and_values: - choices = list(params_and_values[cat].keys()) - if shared.args.loader is not None: - choices = [x for x in choices if loader_contains(x)] - - if len(choices) > 0: - choice = random.choice(choices) - value = random.choice(params_and_values[cat][choice]) - if choice == 'dynamic_temperature': - generate_params['dynamic_temperature'] = True - generate_params['dynatemp_low'] = value[0] - generate_params['dynatemp_high'] = value[1] - else: - generate_params[choice] = value - +def reset_preset_for_ui(name, state): + """Reset current preset to its saved values from file""" + generate_params = load_preset(name, verbose=True) + state.update(generate_params) + return state, *[generate_params[k] for k in presets_params()] + + +def neutralize_samplers_for_ui(state): + """Set all samplers to their default/neutral values""" + generate_params = default_preset() state.update(generate_params) - logger.info("GENERATED_PRESET=") - pprint.PrettyPrinter(indent=4, width=1, sort_dicts=False).pprint(remove_defaults(state)) return state, *[generate_params[k] for k in presets_params()] diff --git a/modules/shared.py b/modules/shared.py index 2e500779..f4f8e180 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -39,10 +39,6 @@ settings = { 'web_search_pages': 3, 'prompt-default': 'QA', 'prompt-notebook': 'QA', - 'character': 'Assistant', - 'name1': 'You', - 'user_bio': '', - 'custom_system_message': '', 'preset': 'min_p', 'max_new_tokens': 512, 'max_new_tokens_min': 1, @@ -63,8 +59,64 @@ settings = { 'negative_prompt': '', 'dark_theme': True, 'default_extensions': [], + + # Character settings + 'character': 'Assistant', + 'name1': 'You', + 'name2': 'AI', + 'user_bio': '', + 'context': 'The following is a conversation with an AI Large Language Model. The AI has been trained to answer questions, provide recommendations, and help with decision making. The AI follows user requests. The AI thinks outside the box.', + 'greeting': 'How can I help you today?', + 'custom_system_message': '', 'instruction_template_str': "{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{%- if not ns.found -%}\n {{- '' + 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' + '\\n\\n' -}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' -%}\n {{- '' + message['content'] + '\\n\\n' -}}\n {%- else -%}\n {%- if message['role'] == 'user' -%}\n {{-'### Instruction:\\n' + message['content'] + '\\n\\n'-}}\n {%- else -%}\n {{-'### Response:\\n' + message['content'] + '\\n\\n' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{-'### Response:\\n'-}}\n{%- endif -%}", 'chat_template_str': "{%- for message in messages %}\n {%- if message['role'] == 'system' -%}\n {%- if message['content'] -%}\n {{- message['content'] + '\\n\\n' -}}\n {%- endif -%}\n {%- if user_bio -%}\n {{- user_bio + '\\n\\n' -}}\n {%- endif -%}\n {%- else -%}\n {%- if message['role'] == 'user' -%}\n {{- name1 + ': ' + message['content'] + '\\n'-}}\n {%- else -%}\n {{- name2 + ': ' + message['content'] + '\\n' -}}\n {%- endif -%}\n {%- endif -%}\n{%- endfor -%}", + + # Generation parameters - Curve shape + 'temperature': 1.0, + 'dynatemp_low': 1.0, + 'dynatemp_high': 1.0, + 'dynatemp_exponent': 1.0, + 'smoothing_factor': 0.0, + 'smoothing_curve': 1.0, + + # Generation parameters - Curve cutoff + 'min_p': 0.0, + 'top_p': 1.0, + 'top_k': 0, + 'typical_p': 1.0, + 'xtc_threshold': 0.1, + 'xtc_probability': 0.0, + 'epsilon_cutoff': 0.0, + 'eta_cutoff': 0.0, + 'tfs': 1.0, + 'top_a': 0.0, + 'top_n_sigma': 0.0, + + # Generation parameters - Repetition suppression + 'dry_multiplier': 0.0, + 'dry_allowed_length': 2, + 'dry_base': 1.75, + 'repetition_penalty': 1.0, + 'frequency_penalty': 0.0, + 'presence_penalty': 0.0, + 'encoder_repetition_penalty': 1.0, + 'no_repeat_ngram_size': 0, + 'repetition_penalty_range': 1024, + + # Generation parameters - Alternative sampling methods + 'penalty_alpha': 0.0, + 'guidance_scale': 1.0, + 'mirostat_mode': 0, + 'mirostat_tau': 5.0, + 'mirostat_eta': 0.1, + + # Generation parameters - Other options + 'do_sample': True, + 'dynamic_temperature': False, + 'temperature_last': False, + 'sampler_priority': 'repetition_penalty\npresence_penalty\nfrequency_penalty\ndry\ntop_n_sigma\ntemperature\ndynamic_temperature\nquadratic_sampling\ntop_k\ntop_p\ntypical_p\nepsilon_cutoff\neta_cutoff\ntfs\ntop_a\nmin_p\nmirostat\nxtc\nencoder_repetition_penalty\nno_repeat_ngram', + 'dry_sequence_breakers': '"\\n", ":", "\\"", "*"', + 'grammar_string': '', } default_settings = copy.deepcopy(settings) @@ -75,7 +127,6 @@ parser = argparse.ArgumentParser(description="Text generation web UI", conflict_ # Basic settings group = parser.add_argument_group('Basic settings') group.add_argument('--multi-user', action='store_true', help='Multi-user mode. Chat histories are not saved or automatically loaded. Warning: this is likely not safe for sharing publicly.') -group.add_argument('--character', type=str, help='The name of the character to load in chat mode by default.') group.add_argument('--model', type=str, help='Name of the model to load by default.') group.add_argument('--lora', type=str, nargs='+', help='The list of LoRAs to load. If you want to load more than one LoRA, write the names separated by spaces.') group.add_argument('--model-dir', type=str, default='user_data/models', help='Path to directory with all the models.') diff --git a/modules/ui.py b/modules/ui.py index db3adf0f..8ec4b165 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -310,7 +310,7 @@ def apply_interface_values(state, use_persistent=False): def save_settings(state, preset, extensions_list, show_controls, theme_state): output = copy.deepcopy(shared.settings) - exclude = ['name2', 'greeting', 'context', 'truncation_length', 'instruction_template_str'] + exclude = [] for k in state: if k in shared.settings and k not in exclude: output[k] = state[k] @@ -323,6 +323,7 @@ def save_settings(state, preset, extensions_list, show_controls, theme_state): output['seed'] = int(output['seed']) output['show_controls'] = show_controls output['dark_theme'] = True if theme_state == 'dark' else False + output.pop('instruction_template_str') # Save extension values in the UI for extension_name in extensions_list: @@ -364,7 +365,7 @@ def store_current_state_and_debounce(interface_state, preset, extensions, show_c if _auto_save_timer is not None: _auto_save_timer.cancel() - _auto_save_timer = threading.Timer(2.0, _perform_debounced_save) + _auto_save_timer = threading.Timer(1.0, _perform_debounced_save) _auto_save_timer.start() @@ -401,15 +402,52 @@ def setup_auto_save(): 'chat-instruct_command', 'character_menu', 'name1', + 'name2', + 'context', + 'greeting', 'user_bio', 'custom_system_message', 'chat_template_str', - # Parameters tab (ui_parameters.py) + # Parameters tab (ui_parameters.py) - Generation parameters 'preset_menu', + 'temperature', + 'dynatemp_low', + 'dynatemp_high', + 'dynatemp_exponent', + 'smoothing_factor', + 'smoothing_curve', + 'min_p', + 'top_p', + 'top_k', + 'typical_p', + 'xtc_threshold', + 'xtc_probability', + 'epsilon_cutoff', + 'eta_cutoff', + 'tfs', + 'top_a', + 'top_n_sigma', + 'dry_multiplier', + 'dry_allowed_length', + 'dry_base', + 'repetition_penalty', + 'frequency_penalty', + 'presence_penalty', + 'encoder_repetition_penalty', + 'no_repeat_ngram_size', + 'repetition_penalty_range', + 'penalty_alpha', + 'guidance_scale', + 'mirostat_mode', + 'mirostat_tau', + 'mirostat_eta', 'max_new_tokens', 'prompt_lookup_num_tokens', 'max_tokens_second', + 'do_sample', + 'dynamic_temperature', + 'temperature_last', 'auto_max_new_tokens', 'ban_eos_token', 'add_bos_token', @@ -417,10 +455,14 @@ def setup_auto_save(): 'skip_special_tokens', 'stream', 'static_cache', + 'truncation_length', 'seed', + 'sampler_priority', 'custom_stopping_strings', 'custom_token_bans', 'negative_prompt', + 'dry_sequence_breakers', + 'grammar_string', # Default tab (ui_default.py) 'prompt_menu-default', diff --git a/modules/ui_chat.py b/modules/ui_chat.py index 0d5a2c18..712843d3 100644 --- a/modules/ui_chat.py +++ b/modules/ui_chat.py @@ -86,7 +86,7 @@ def create_ui(): shared.gradio['web_search_pages'] = gr.Number(value=shared.settings.get('web_search_pages', 3), precision=0, label='Number of pages to download', minimum=1, maximum=10) with gr.Row(): - shared.gradio['mode'] = gr.Radio(choices=['instruct', 'chat-instruct', 'chat'], value=shared.settings['mode'] if shared.settings['mode'] in ['chat', 'chat-instruct'] else None, label='Mode', info='Defines how the chat prompt is generated. In instruct and chat-instruct modes, the instruction template Parameters > Instruction template is used.', elem_id='chat-mode') + shared.gradio['mode'] = gr.Radio(choices=['instruct', 'chat-instruct', 'chat'], value=None, label='Mode', info='Defines how the chat prompt is generated. In instruct and chat-instruct modes, the instruction template Parameters > Instruction template is used.', elem_id='chat-mode') with gr.Row(): shared.gradio['chat_style'] = gr.Dropdown(choices=utils.get_available_chat_styles(), label='Chat style', value=shared.settings['chat_style'], visible=shared.settings['mode'] != 'instruct') @@ -118,14 +118,16 @@ def create_chat_settings_ui(): with gr.Column(scale=8): with gr.Tab("Character"): with gr.Row(): - shared.gradio['character_menu'] = gr.Dropdown(value=None, choices=utils.get_available_characters(), label='Character', elem_id='character-menu', info='Used in chat and chat-instruct modes.', elem_classes='slim-dropdown') + shared.gradio['character_menu'] = gr.Dropdown(value=shared.settings['character'], choices=utils.get_available_characters(), label='Character', elem_id='character-menu', info='Used in chat and chat-instruct modes.', elem_classes='slim-dropdown') ui.create_refresh_button(shared.gradio['character_menu'], lambda: None, lambda: {'choices': utils.get_available_characters()}, 'refresh-button', interactive=not mu) shared.gradio['save_character'] = gr.Button('💾', elem_classes='refresh-button', elem_id="save-character", interactive=not mu) shared.gradio['delete_character'] = gr.Button('🗑️', elem_classes='refresh-button', interactive=not mu) + shared.gradio['reset_character'] = gr.Button('↺', elem_classes='refresh-button', interactive=True) + shared.gradio['clear_character'] = gr.Button('⚪', elem_classes='refresh-button', interactive=True) - shared.gradio['name2'] = gr.Textbox(value='', lines=1, label='Character\'s name') - shared.gradio['context'] = gr.Textbox(value='', lines=10, label='Context', elem_classes=['add_scrollbar']) - shared.gradio['greeting'] = gr.Textbox(value='', lines=5, label='Greeting', elem_classes=['add_scrollbar']) + shared.gradio['name2'] = gr.Textbox(value=shared.settings['name2'], lines=1, label='Character\'s name') + shared.gradio['context'] = gr.Textbox(value=shared.settings['context'], lines=10, label='Context', elem_classes=['add_scrollbar']) + shared.gradio['greeting'] = gr.Textbox(value=shared.settings['greeting'], lines=5, label='Greeting', elem_classes=['add_scrollbar']) with gr.Tab("User"): shared.gradio['name1'] = gr.Textbox(value=shared.settings['name1'], lines=1, label='Name') @@ -178,7 +180,7 @@ def create_chat_settings_ui(): with gr.Row(): with gr.Column(): shared.gradio['custom_system_message'] = gr.Textbox(value=shared.settings['custom_system_message'], lines=2, label='Custom system message', info='If not empty, will be used instead of the default one.', elem_classes=['add_scrollbar']) - shared.gradio['instruction_template_str'] = gr.Textbox(value='', label='Instruction template', lines=24, info='This gets autodetected; you usually don\'t need to change it. Used in instruct and chat-instruct modes.', elem_classes=['add_scrollbar', 'monospace']) + shared.gradio['instruction_template_str'] = gr.Textbox(value=shared.settings['instruction_template_str'], label='Instruction template', lines=24, info='This gets autodetected; you usually don\'t need to change it. Used in instruct and chat-instruct modes.', elem_classes=['add_scrollbar', 'monospace']) 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']) @@ -294,6 +296,8 @@ def create_event_handlers(): chat.handle_character_menu_change, gradio('interface_state'), gradio('history', 'display', 'name1', 'name2', 'character_picture', 'greeting', 'context', 'unique_id'), show_progress=False).then( None, None, None, js=f'() => {{{ui.update_big_picture_js}; updateBigPicture()}}') + shared.gradio['character_picture'].change(chat.handle_character_picture_change, gradio('character_picture'), None, show_progress=False) + shared.gradio['mode'].change( ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then( chat.handle_mode_change, gradio('interface_state'), gradio('history', 'display', 'chat_style', 'chat-instruct_command', 'unique_id'), show_progress=False).then( @@ -317,6 +321,10 @@ def create_event_handlers(): ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then( chat.handle_save_template_click, gradio('instruction_template_str'), gradio('save_filename', 'save_root', 'save_contents', 'file_saver'), show_progress=False) + shared.gradio['reset_character'].click( + ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then( + chat.reset_character_for_ui, gradio('interface_state'), gradio('interface_state', 'name2', 'context', 'greeting', 'character_picture'), show_progress=False) + shared.gradio['delete_template'].click(chat.handle_delete_template_click, gradio('instruction_template'), gradio('delete_filename', 'delete_root', 'file_deleter'), show_progress=False) shared.gradio['save_chat_history'].click( lambda x: json.dumps(x, indent=4), gradio('history'), gradio('temporary_text')).then( diff --git a/modules/ui_default.py b/modules/ui_default.py index c2946b37..8acc4b10 100644 --- a/modules/ui_default.py +++ b/modules/ui_default.py @@ -19,7 +19,7 @@ def create_ui(): with gr.Row(): with gr.Column(): with gr.Row(): - shared.gradio['textbox-default'] = gr.Textbox(value='', lines=27, label='Input', elem_classes=['textbox_default', 'add_scrollbar']) + shared.gradio['textbox-default'] = gr.Textbox(value=load_prompt(shared.settings['prompt-default']), lines=27, label='Input', elem_classes=['textbox_default', 'add_scrollbar']) shared.gradio['token-counter-default'] = gr.HTML(value="0", elem_id="default-token-counter") with gr.Row(): @@ -28,7 +28,7 @@ def create_ui(): shared.gradio['Generate-default'] = gr.Button('Generate', variant='primary') with gr.Row(): - shared.gradio['prompt_menu-default'] = gr.Dropdown(choices=utils.get_available_prompts(), value='None', label='Prompt', elem_classes='slim-dropdown') + shared.gradio['prompt_menu-default'] = gr.Dropdown(choices=utils.get_available_prompts(), value=shared.settings['prompt-default'], label='Prompt', elem_classes='slim-dropdown') ui.create_refresh_button(shared.gradio['prompt_menu-default'], lambda: None, lambda: {'choices': utils.get_available_prompts()}, 'refresh-button', interactive=not mu) shared.gradio['save_prompt-default'] = gr.Button('💾', elem_classes='refresh-button', interactive=not mu) shared.gradio['delete_prompt-default'] = gr.Button('🗑️', elem_classes='refresh-button', interactive=not mu) diff --git a/modules/ui_notebook.py b/modules/ui_notebook.py index b234ac57..3f79a93c 100644 --- a/modules/ui_notebook.py +++ b/modules/ui_notebook.py @@ -22,7 +22,7 @@ def create_ui(): with gr.Column(scale=4): with gr.Tab('Raw'): with gr.Row(): - shared.gradio['textbox-notebook'] = gr.Textbox(value='', lines=27, elem_id='textbox-notebook', elem_classes=['textbox', 'add_scrollbar']) + shared.gradio['textbox-notebook'] = gr.Textbox(value=load_prompt(shared.settings['prompt-notebook']), lines=27, elem_id='textbox-notebook', elem_classes=['textbox', 'add_scrollbar']) shared.gradio['token-counter-notebook'] = gr.HTML(value="0", elem_id="notebook-token-counter") with gr.Tab('Markdown'): @@ -56,7 +56,7 @@ def create_ui(): with gr.Column(scale=1): gr.HTML('
') with gr.Row(): - shared.gradio['prompt_menu-notebook'] = gr.Dropdown(choices=utils.get_available_prompts(), value='None', label='Prompt', elem_classes='slim-dropdown') + shared.gradio['prompt_menu-notebook'] = gr.Dropdown(choices=utils.get_available_prompts(), value=shared.settings['prompt-notebook'], label='Prompt', elem_classes='slim-dropdown') ui.create_refresh_button(shared.gradio['prompt_menu-notebook'], lambda: None, lambda: {'choices': utils.get_available_prompts()}, ['refresh-button', 'refresh-button-small'], interactive=not mu) shared.gradio['save_prompt-notebook'] = gr.Button('💾', elem_classes=['refresh-button', 'refresh-button-small'], interactive=not mu) shared.gradio['delete_prompt-notebook'] = gr.Button('🗑️', elem_classes=['refresh-button', 'refresh-button-small'], interactive=not mu) diff --git a/modules/ui_parameters.py b/modules/ui_parameters.py index 84f9fbfc..ff965d39 100644 --- a/modules/ui_parameters.py +++ b/modules/ui_parameters.py @@ -6,19 +6,19 @@ from modules import loaders, presets, shared, ui, ui_chat, utils from modules.utils import gradio -def create_ui(default_preset): +def create_ui(): mu = shared.args.multi_user - generate_params = presets.load_preset(default_preset) with gr.Tab("Parameters", elem_id="parameters"): with gr.Tab("Generation"): with gr.Row(): with gr.Column(): with gr.Row(): - shared.gradio['preset_menu'] = gr.Dropdown(choices=utils.get_available_presets(), value=default_preset, label='Preset', elem_classes='slim-dropdown') + shared.gradio['preset_menu'] = gr.Dropdown(choices=utils.get_available_presets(), value=shared.settings['preset'], label='Preset', elem_classes='slim-dropdown') ui.create_refresh_button(shared.gradio['preset_menu'], lambda: None, lambda: {'choices': utils.get_available_presets()}, 'refresh-button', interactive=not mu) shared.gradio['save_preset'] = gr.Button('💾', elem_classes='refresh-button', interactive=not mu) shared.gradio['delete_preset'] = gr.Button('🗑️', elem_classes='refresh-button', interactive=not mu) - shared.gradio['random_preset'] = gr.Button('🎲', elem_classes='refresh-button') + shared.gradio['reset_preset'] = gr.Button('Reload preset', elem_classes='refresh-button', interactive=True) + shared.gradio['neutralize_samplers'] = gr.Button('Neutralize samplers', elem_classes='refresh-button', interactive=True) with gr.Column(): shared.gradio['filter_by_loader'] = gr.Dropdown(label="Filter by loader", choices=["All"] + list(loaders.loaders_and_params.keys()) if not shared.args.portable else ['llama.cpp'], value="All", elem_classes='slim-dropdown') @@ -28,44 +28,44 @@ def create_ui(default_preset): with gr.Row(): with gr.Column(): gr.Markdown('## Curve shape') - shared.gradio['temperature'] = gr.Slider(0.01, 5, value=generate_params['temperature'], step=0.01, label='temperature') - shared.gradio['dynatemp_low'] = gr.Slider(0.01, 5, value=generate_params['dynatemp_low'], step=0.01, label='dynatemp_low', visible=generate_params['dynamic_temperature']) - shared.gradio['dynatemp_high'] = gr.Slider(0.01, 5, value=generate_params['dynatemp_high'], step=0.01, label='dynatemp_high', visible=generate_params['dynamic_temperature']) - shared.gradio['dynatemp_exponent'] = gr.Slider(0.01, 5, value=generate_params['dynatemp_exponent'], step=0.01, label='dynatemp_exponent', visible=generate_params['dynamic_temperature']) - shared.gradio['smoothing_factor'] = gr.Slider(0.0, 10.0, value=generate_params['smoothing_factor'], step=0.01, label='smoothing_factor', info='Activates Quadratic Sampling.') - shared.gradio['smoothing_curve'] = gr.Slider(1.0, 10.0, value=generate_params['smoothing_curve'], step=0.01, label='smoothing_curve', info='Adjusts the dropoff curve of Quadratic Sampling.') + shared.gradio['temperature'] = gr.Slider(0.01, 5, value=shared.settings['temperature'], step=0.01, label='temperature') + shared.gradio['dynatemp_low'] = gr.Slider(0.01, 5, value=shared.settings['dynatemp_low'], step=0.01, label='dynatemp_low', visible=shared.settings['dynamic_temperature']) + shared.gradio['dynatemp_high'] = gr.Slider(0.01, 5, value=shared.settings['dynatemp_high'], step=0.01, label='dynatemp_high', visible=shared.settings['dynamic_temperature']) + shared.gradio['dynatemp_exponent'] = gr.Slider(0.01, 5, value=shared.settings['dynatemp_exponent'], step=0.01, label='dynatemp_exponent', visible=shared.settings['dynamic_temperature']) + shared.gradio['smoothing_factor'] = gr.Slider(0.0, 10.0, value=shared.settings['smoothing_factor'], step=0.01, label='smoothing_factor', info='Activates Quadratic Sampling.') + shared.gradio['smoothing_curve'] = gr.Slider(1.0, 10.0, value=shared.settings['smoothing_curve'], step=0.01, label='smoothing_curve', info='Adjusts the dropoff curve of Quadratic Sampling.') gr.Markdown('## Curve cutoff') - shared.gradio['min_p'] = gr.Slider(0.0, 1.0, value=generate_params['min_p'], step=0.01, label='min_p') - shared.gradio['top_n_sigma'] = gr.Slider(0.0, 5.0, value=generate_params['top_n_sigma'], step=0.01, label='top_n_sigma') - shared.gradio['top_p'] = gr.Slider(0.0, 1.0, value=generate_params['top_p'], step=0.01, label='top_p') - shared.gradio['top_k'] = gr.Slider(0, 200, value=generate_params['top_k'], step=1, label='top_k') - shared.gradio['typical_p'] = gr.Slider(0.0, 1.0, value=generate_params['typical_p'], step=0.01, label='typical_p') - shared.gradio['xtc_threshold'] = gr.Slider(0, 0.5, value=generate_params['xtc_threshold'], step=0.01, label='xtc_threshold', info='If 2 or more tokens have probability above this threshold, consider removing all but the last one.') - shared.gradio['xtc_probability'] = gr.Slider(0, 1, value=generate_params['xtc_probability'], step=0.01, label='xtc_probability', info='Probability that the removal will actually happen. 0 disables the sampler. 1 makes it always happen.') - shared.gradio['epsilon_cutoff'] = gr.Slider(0, 9, value=generate_params['epsilon_cutoff'], step=0.01, label='epsilon_cutoff') - shared.gradio['eta_cutoff'] = gr.Slider(0, 20, value=generate_params['eta_cutoff'], step=0.01, label='eta_cutoff') - shared.gradio['tfs'] = gr.Slider(0.0, 1.0, value=generate_params['tfs'], step=0.01, label='tfs') - shared.gradio['top_a'] = gr.Slider(0.0, 1.0, value=generate_params['top_a'], step=0.01, label='top_a') + shared.gradio['min_p'] = gr.Slider(0.0, 1.0, value=shared.settings['min_p'], step=0.01, label='min_p') + shared.gradio['top_n_sigma'] = gr.Slider(0.0, 5.0, value=shared.settings['top_n_sigma'], step=0.01, label='top_n_sigma') + shared.gradio['top_p'] = gr.Slider(0.0, 1.0, value=shared.settings['top_p'], step=0.01, label='top_p') + shared.gradio['top_k'] = gr.Slider(0, 200, value=shared.settings['top_k'], step=1, label='top_k') + shared.gradio['typical_p'] = gr.Slider(0.0, 1.0, value=shared.settings['typical_p'], step=0.01, label='typical_p') + shared.gradio['xtc_threshold'] = gr.Slider(0, 0.5, value=shared.settings['xtc_threshold'], step=0.01, label='xtc_threshold', info='If 2 or more tokens have probability above this threshold, consider removing all but the last one.') + shared.gradio['xtc_probability'] = gr.Slider(0, 1, value=shared.settings['xtc_probability'], step=0.01, label='xtc_probability', info='Probability that the removal will actually happen. 0 disables the sampler. 1 makes it always happen.') + shared.gradio['epsilon_cutoff'] = gr.Slider(0, 9, value=shared.settings['epsilon_cutoff'], step=0.01, label='epsilon_cutoff') + shared.gradio['eta_cutoff'] = gr.Slider(0, 20, value=shared.settings['eta_cutoff'], step=0.01, label='eta_cutoff') + shared.gradio['tfs'] = gr.Slider(0.0, 1.0, value=shared.settings['tfs'], step=0.01, label='tfs') + shared.gradio['top_a'] = gr.Slider(0.0, 1.0, value=shared.settings['top_a'], step=0.01, label='top_a') gr.Markdown('## Repetition suppression') - shared.gradio['dry_multiplier'] = gr.Slider(0, 5, value=generate_params['dry_multiplier'], step=0.01, label='dry_multiplier', info='Set to greater than 0 to enable DRY. Recommended value: 0.8.') - shared.gradio['dry_allowed_length'] = gr.Slider(1, 20, value=generate_params['dry_allowed_length'], step=1, label='dry_allowed_length', info='Longest sequence that can be repeated without being penalized.') - shared.gradio['dry_base'] = gr.Slider(1, 4, value=generate_params['dry_base'], step=0.01, label='dry_base', info='Controls how fast the penalty grows with increasing sequence length.') - shared.gradio['repetition_penalty'] = gr.Slider(1.0, 1.5, value=generate_params['repetition_penalty'], step=0.01, label='repetition_penalty') - shared.gradio['frequency_penalty'] = gr.Slider(0, 2, value=generate_params['frequency_penalty'], step=0.05, label='frequency_penalty') - shared.gradio['presence_penalty'] = gr.Slider(0, 2, value=generate_params['presence_penalty'], step=0.05, label='presence_penalty') - shared.gradio['encoder_repetition_penalty'] = gr.Slider(0.8, 1.5, value=generate_params['encoder_repetition_penalty'], step=0.01, label='encoder_repetition_penalty') - shared.gradio['no_repeat_ngram_size'] = gr.Slider(0, 20, step=1, value=generate_params['no_repeat_ngram_size'], label='no_repeat_ngram_size') - shared.gradio['repetition_penalty_range'] = gr.Slider(0, 4096, step=64, value=generate_params['repetition_penalty_range'], label='repetition_penalty_range') + shared.gradio['dry_multiplier'] = gr.Slider(0, 5, value=shared.settings['dry_multiplier'], step=0.01, label='dry_multiplier', info='Set to greater than 0 to enable DRY. Recommended value: 0.8.') + shared.gradio['dry_allowed_length'] = gr.Slider(1, 20, value=shared.settings['dry_allowed_length'], step=1, label='dry_allowed_length', info='Longest sequence that can be repeated without being penalized.') + shared.gradio['dry_base'] = gr.Slider(1, 4, value=shared.settings['dry_base'], step=0.01, label='dry_base', info='Controls how fast the penalty grows with increasing sequence length.') + shared.gradio['repetition_penalty'] = gr.Slider(1.0, 1.5, value=shared.settings['repetition_penalty'], step=0.01, label='repetition_penalty') + shared.gradio['frequency_penalty'] = gr.Slider(0, 2, value=shared.settings['frequency_penalty'], step=0.05, label='frequency_penalty') + shared.gradio['presence_penalty'] = gr.Slider(0, 2, value=shared.settings['presence_penalty'], step=0.05, label='presence_penalty') + shared.gradio['encoder_repetition_penalty'] = gr.Slider(0.8, 1.5, value=shared.settings['encoder_repetition_penalty'], step=0.01, label='encoder_repetition_penalty') + shared.gradio['no_repeat_ngram_size'] = gr.Slider(0, 20, step=1, value=shared.settings['no_repeat_ngram_size'], label='no_repeat_ngram_size') + shared.gradio['repetition_penalty_range'] = gr.Slider(0, 4096, step=64, value=shared.settings['repetition_penalty_range'], label='repetition_penalty_range') with gr.Column(): gr.Markdown('## Alternative sampling methods') - shared.gradio['penalty_alpha'] = gr.Slider(0, 5, value=generate_params['penalty_alpha'], label='penalty_alpha', info='For Contrastive Search. do_sample must be unchecked.') - shared.gradio['guidance_scale'] = gr.Slider(-0.5, 2.5, step=0.05, value=generate_params['guidance_scale'], label='guidance_scale', info='For CFG. 1.5 is a good value.') - shared.gradio['mirostat_mode'] = gr.Slider(0, 2, step=1, value=generate_params['mirostat_mode'], label='mirostat_mode', info='mode=1 is for llama.cpp only.') - shared.gradio['mirostat_tau'] = gr.Slider(0, 10, step=0.01, value=generate_params['mirostat_tau'], label='mirostat_tau') - shared.gradio['mirostat_eta'] = gr.Slider(0, 1, step=0.01, value=generate_params['mirostat_eta'], label='mirostat_eta') + shared.gradio['penalty_alpha'] = gr.Slider(0, 5, value=shared.settings['penalty_alpha'], label='penalty_alpha', info='For Contrastive Search. do_sample must be unchecked.') + shared.gradio['guidance_scale'] = gr.Slider(-0.5, 2.5, step=0.05, value=shared.settings['guidance_scale'], label='guidance_scale', info='For CFG. 1.5 is a good value.') + shared.gradio['mirostat_mode'] = gr.Slider(0, 2, step=1, value=shared.settings['mirostat_mode'], label='mirostat_mode', info='mode=1 is for llama.cpp only.') + shared.gradio['mirostat_tau'] = gr.Slider(0, 10, step=0.01, value=shared.settings['mirostat_tau'], label='mirostat_tau') + shared.gradio['mirostat_eta'] = gr.Slider(0, 1, step=0.01, value=shared.settings['mirostat_eta'], label='mirostat_eta') gr.Markdown('## Other options') shared.gradio['max_new_tokens'] = gr.Slider(minimum=shared.settings['max_new_tokens_min'], maximum=shared.settings['max_new_tokens_max'], value=shared.settings['max_new_tokens'], step=1, label='max_new_tokens', info='⚠️ Setting this too high can cause prompt truncation.') @@ -74,9 +74,9 @@ def create_ui(default_preset): with gr.Column(): with gr.Row(): with gr.Column(): - shared.gradio['do_sample'] = gr.Checkbox(value=generate_params['do_sample'], label='do_sample') - shared.gradio['dynamic_temperature'] = gr.Checkbox(value=generate_params['dynamic_temperature'], label='dynamic_temperature') - shared.gradio['temperature_last'] = gr.Checkbox(value=generate_params['temperature_last'], label='temperature_last', info='Moves temperature/dynamic temperature/quadratic sampling to the end of the sampler stack, ignoring their positions in "Sampler priority".') + shared.gradio['do_sample'] = gr.Checkbox(value=shared.settings['do_sample'], label='do_sample') + shared.gradio['dynamic_temperature'] = gr.Checkbox(value=shared.settings['dynamic_temperature'], label='dynamic_temperature') + shared.gradio['temperature_last'] = gr.Checkbox(value=shared.settings['temperature_last'], label='temperature_last', info='Moves temperature/dynamic temperature/quadratic sampling to the end of the sampler stack, ignoring their positions in "Sampler priority".') shared.gradio['auto_max_new_tokens'] = gr.Checkbox(value=shared.settings['auto_max_new_tokens'], label='auto_max_new_tokens', info='Expand max_new_tokens to the available context length.') shared.gradio['ban_eos_token'] = gr.Checkbox(value=shared.settings['ban_eos_token'], label='Ban the eos_token', info='Forces the model to never end the generation prematurely.') 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.') @@ -89,18 +89,18 @@ def create_ui(default_preset): shared.gradio['truncation_length'] = gr.Number(precision=0, step=256, value=get_truncation_length(), label='Truncate the prompt up to this length', info='The leftmost tokens are removed if the prompt exceeds this length.') shared.gradio['seed'] = gr.Number(value=shared.settings['seed'], label='Seed (-1 for random)') - shared.gradio['sampler_priority'] = gr.Textbox(value=generate_params['sampler_priority'], lines=12, label='Sampler priority', info='Parameter names separated by new lines or commas.', elem_classes=['add_scrollbar']) + shared.gradio['sampler_priority'] = gr.Textbox(value=shared.settings['sampler_priority'], lines=12, label='Sampler priority', info='Parameter names separated by new lines or commas.', elem_classes=['add_scrollbar']) shared.gradio['custom_stopping_strings'] = gr.Textbox(lines=2, value=shared.settings["custom_stopping_strings"] or None, label='Custom stopping strings', info='Written between "" and separated by commas.', placeholder='"\\n", "\\nYou:"') shared.gradio['custom_token_bans'] = gr.Textbox(value=shared.settings['custom_token_bans'] or None, label='Token bans', info='Token IDs to ban, separated by commas. The IDs can be found in the Default or Notebook tab.') shared.gradio['negative_prompt'] = gr.Textbox(value=shared.settings['negative_prompt'], label='Negative prompt', info='For CFG. Only used when guidance_scale is different than 1.', lines=3, elem_classes=['add_scrollbar']) - shared.gradio['dry_sequence_breakers'] = gr.Textbox(value=generate_params['dry_sequence_breakers'], label='dry_sequence_breakers', info='Tokens across which sequence matching is not continued. Specified as a comma-separated list of quoted strings.') + shared.gradio['dry_sequence_breakers'] = gr.Textbox(value=shared.settings['dry_sequence_breakers'], label='dry_sequence_breakers', info='Tokens across which sequence matching is not continued. Specified as a comma-separated list of quoted strings.') with gr.Row() as shared.gradio['grammar_file_row']: shared.gradio['grammar_file'] = gr.Dropdown(value='None', choices=utils.get_available_grammars(), label='Load grammar from file (.gbnf)', elem_classes='slim-dropdown') ui.create_refresh_button(shared.gradio['grammar_file'], lambda: None, lambda: {'choices': utils.get_available_grammars()}, 'refresh-button', interactive=not mu) shared.gradio['save_grammar'] = gr.Button('💾', elem_classes='refresh-button', interactive=not mu) shared.gradio['delete_grammar'] = gr.Button('🗑️ ', elem_classes='refresh-button', interactive=not mu) - shared.gradio['grammar_string'] = gr.Textbox(value='', label='Grammar', lines=16, elem_classes=['add_scrollbar', 'monospace']) + shared.gradio['grammar_string'] = gr.Textbox(value=shared.settings['grammar_string'], label='Grammar', lines=16, elem_classes=['add_scrollbar', 'monospace']) ui_chat.create_chat_settings_ui() @@ -111,9 +111,13 @@ def create_event_handlers(): ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then( presets.load_preset_for_ui, gradio('preset_menu', 'interface_state'), gradio('interface_state') + gradio(presets.presets_params()), show_progress=False) - shared.gradio['random_preset'].click( + shared.gradio['reset_preset'].click( ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then( - presets.random_preset, gradio('interface_state'), gradio('interface_state') + gradio(presets.presets_params()), show_progress=False) + presets.reset_preset_for_ui, gradio('preset_menu', 'interface_state'), gradio('interface_state') + gradio(presets.presets_params()), show_progress=False) + + shared.gradio['neutralize_samplers'].click( + ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then( + presets.neutralize_samplers_for_ui, gradio('interface_state'), gradio('interface_state') + gradio(presets.presets_params()), show_progress=False) shared.gradio['grammar_file'].change(load_grammar, gradio('grammar_file'), gradio('grammar_string'), show_progress=False) shared.gradio['dynamic_temperature'].change(lambda x: [gr.update(visible=x)] * 3, gradio('dynamic_temperature'), gradio('dynatemp_low', 'dynatemp_high', 'dynatemp_exponent'), show_progress=False) diff --git a/server.py b/server.py index 3be4c27c..3dd0a3f3 100644 --- a/server.py +++ b/server.py @@ -45,6 +45,7 @@ from modules import ( ui_session, utils ) +from modules.chat import generate_pfp_cache from modules.extensions import apply_extensions from modules.LoRA import add_lora_to_model from modules.models import load_model, unload_model_if_idle @@ -93,17 +94,20 @@ def create_interface(): # Force some events to be triggered on page load shared.persistent_interface_state.update({ + 'mode': shared.settings['mode'], 'loader': shared.args.loader or 'llama.cpp', - 'mode': shared.settings['mode'] if shared.settings['mode'] == 'instruct' else gr.update(), - 'character_menu': shared.args.character or shared.settings['character'], - 'instruction_template_str': shared.settings['instruction_template_str'], - 'prompt_menu-default': shared.settings['prompt-default'], - 'prompt_menu-notebook': shared.settings['prompt-notebook'], 'filter_by_loader': (shared.args.loader or 'All') if not shared.args.portable else 'llama.cpp' }) - if Path("user_data/cache/pfp_character.png").exists(): - Path("user_data/cache/pfp_character.png").unlink() + # Clear existing cache files + for cache_file in ['pfp_character.png', 'pfp_character_thumb.png']: + cache_path = Path(f"user_data/cache/{cache_file}") + if cache_path.exists(): + cache_path.unlink() + + # Regenerate for default character + if shared.settings['mode'] != 'instruct': + generate_pfp_cache(shared.settings['character']) # css/js strings css = ui.css @@ -134,7 +138,7 @@ def create_interface(): ui_default.create_ui() ui_notebook.create_ui() - ui_parameters.create_ui(shared.settings['preset']) # Parameters tab + ui_parameters.create_ui() # Parameters tab ui_model_menu.create_ui() # Model tab if not shared.args.portable: training.create_ui() # Training tab