Merge pull request #5772 from oobabooga/dev

Merge dev branch

css/main.css

@@ -89,6 +89,11 @@ div.svelte-15lo0d8 > *, div.svelte-15lo0d8 > .form > * {
     flex-wrap: nowrap;
 }
 
+gradio-app > :first-child {
+    padding-left: var(--size-4) !important;
+    padding-right: var(--size-4) !important;
+}
+
 .header_bar {
     background-color: #f7f7f7;
     box-shadow: 0 2px 3px rgba(22 22 22 / 35%);
@@ -522,6 +527,7 @@ div.svelte-362y77>*, div.svelte-362y77>.form>* {
     position: absolute;
     background-color: transparent;
     left: -2px;
+    top: 4px;
     padding: var(--block-padding);
 }
 

docker/.env.example

@@ -2,8 +2,6 @@
 # however for me to work i had to specify the exact version for my card ( 2060 ) it was 7.5
 # https://developer.nvidia.com/cuda-gpus you can find the version for your card here
 TORCH_CUDA_ARCH_LIST=7.5
-# your command-line flags go here:
-CLI_ARGS=--listen
 # the port the webui binds to on the host
 HOST_PORT=7860
 # the port the webui binds to inside the container

docs/03 - Parameters Tab.md

@@ -61,10 +61,6 @@ For more information about the parameters, the [transformers documentation](http
 * **Seed**: Set the Pytorch seed to this number. Note that some loaders do not use Pytorch (notably llama.cpp), and others are not deterministic (ExLlamaV2). For these loaders, the seed has no effect.
 * **encoder_repetition_penalty**: Also known as the "Hallucinations filter". Used to penalize tokens that are *not* in the prior text. Higher value = more likely to stay in context, lower value = more likely to diverge.
 * **no_repeat_ngram_size**: If not set to 0, specifies the length of token sets that are completely blocked from repeating at all. Higher values = blocks larger phrases, lower values = blocks words or letters from repeating. Only 0 or high values are a good idea in most cases.
-* **min_length**: Minimum generation length in tokens. This is a built-in parameter in the transformers library that has never been very useful. Typically you want to check "Ban the eos_token" instead.
-* **num_beams**: Number of beams for beam search. 1 means no beam search.
-* **length_penalty**: Used by beam search only. `length_penalty > 0.0` promotes longer sequences, while `length_penalty < 0.0` encourages shorter sequences.
-* **early_stopping**: Used by beam search only. When checked, the generation stops as soon as there are "num_beams" complete candidates; otherwise, a heuristic is applied and the generation stops when is it very unlikely to find better candidates (I just copied this from the transformers documentation and have never gotten beam search to generate good results).
 
 To the right (or below if you are on mobile), the following parameters are present:
 

extensions/gallery/script.py

@@ -119,7 +119,7 @@ def ui():
             samples_per_page=settings["gallery-items_per_page"]
         )
 
-    filter_box.change(lambda: None, None, None, _js=f'() => {{{custom_js()}; gotoFirstPage()}}').success(
+    filter_box.change(lambda: None, None, None, js=f'() => {{{custom_js()}; gotoFirstPage()}}').success(
         filter_cards, filter_box, gallery).then(
         lambda x: gr.update(elem_classes='highlighted-border' if x != '' else ''), filter_box, filter_box, show_progress=False)
 

extensions/openai/completions.py

@@ -261,6 +261,7 @@ def chat_completions_common(body: dict, is_legacy: bool = False, stream=False) -
     name2 = body['bot_name'] or name2
     context = body['context'] or context
     greeting = body['greeting'] or greeting
+    user_bio = body['user_bio'] or ''
 
     # History
     user_input, custom_system_message, history = convert_history(messages)
@@ -271,6 +272,7 @@ def chat_completions_common(body: dict, is_legacy: bool = False, stream=False) -
         'name2': name2,
         'context': context,
         'greeting': greeting,
+        'user_bio': user_bio,
         'instruction_template_str': instruction_template_str,
         'custom_system_message': custom_system_message,
         'chat_template_str': chat_template_str,

extensions/openai/typing.py

@@ -33,10 +33,6 @@ class GenerationOptions(BaseModel):
     seed: int = -1
     encoder_repetition_penalty: float = 1
     no_repeat_ngram_size: int = 0
-    min_length: int = 0
-    num_beams: int = 1
-    length_penalty: float = 1
-    early_stopping: bool = False
     truncation_length: int = 0
     max_tokens_second: int = 0
     prompt_lookup_num_tokens: int = 0

extensions/whisper_stt/script.py

@@ -64,7 +64,7 @@ def ui():
 
     audio.change(
         auto_transcribe, [audio, auto_submit, whipser_model, whipser_language], [shared.gradio['textbox'], audio]).then(
-        None, auto_submit, None, _js="(check) => {if (check) { document.getElementById('Generate').click() }}")
+        None, auto_submit, None, js="(check) => {if (check) { document.getElementById('Generate').click() }}")
 
     whipser_model.change(lambda x: params.update({"whipser_model": x}), whipser_model, None)
     whipser_language.change(lambda x: params.update({"whipser_language": x}), whipser_language, None)

js/switch_tabs.js

@@ -32,27 +32,27 @@ function switch_to_chat() {
 }
 
 function switch_to_default() {
-  let default_tab_button = main_parent.childNodes[0].childNodes[4];
+  let default_tab_button = main_parent.childNodes[0].childNodes[5];
   default_tab_button.click();
   scrollToTop();
 }
 
 function switch_to_notebook() {
-  let notebook_tab_button = main_parent.childNodes[0].childNodes[7];
+  let notebook_tab_button = main_parent.childNodes[0].childNodes[9];
   notebook_tab_button.click();
   findButtonsByText("Raw")[1].click();
   scrollToTop();
 }
 
 function switch_to_generation_parameters() {
-  let parameters_tab_button = main_parent.childNodes[0].childNodes[10];
+  let parameters_tab_button = main_parent.childNodes[0].childNodes[13];
   parameters_tab_button.click();
   findButtonsByText("Generation")[0].click();
   scrollToTop();
 }
 
 function switch_to_character() {
-  let parameters_tab_button = main_parent.childNodes[0].childNodes[10];
+  let parameters_tab_button = main_parent.childNodes[0].childNodes[13];
   parameters_tab_button.click();
   findButtonsByText("Character")[0].click();
   scrollToTop();

models/config.yaml

@@ -190,3 +190,5 @@
   instruction_template: 'ChatML'
 .*synthia:
   instruction_template: 'Synthia'
+.*(hercules|hyperion):
+  instruction_template: 'ChatML'

modules/block_requests.py

@@ -43,8 +43,9 @@ def my_open(*args, **kwargs):
         with original_open(*args, **kwargs) as f:
             file_contents = f.read()
 
-        file_contents = file_contents.replace(b'\t\t<script\n\t\t\tsrc="https://cdnjs.cloudflare.com/ajax/libs/iframe-resizer/4.3.7/iframeResizer.contentWindow.min.js"\n\t\t\tasync\n\t\t></script>', b'')
+        file_contents = file_contents.replace(b'\t\t<script\n\t\t\tsrc="https://cdnjs.cloudflare.com/ajax/libs/iframe-resizer/4.3.9/iframeResizer.contentWindow.min.js"\n\t\t\tasync\n\t\t></script>', b'')
         file_contents = file_contents.replace(b'cdnjs.cloudflare.com', b'127.0.0.1')
+
         return io.BytesIO(file_contents)
     else:
         return original_open(*args, **kwargs)

modules/chat.py

@@ -161,12 +161,14 @@ def generate_chat_prompt(user_input, state, **kwargs):
 
             prompt = instruction_template.render(messages=outer_messages)
             suffix = get_generation_prompt(instruct_renderer, impersonate=False)[1]
-            prompt = prompt[:-len(suffix)]
+            if len(suffix) > 0:
+                prompt = prompt[:-len(suffix)]
 
         else:
             if _continue:
                 suffix = get_generation_prompt(renderer, impersonate=impersonate)[1]
-                prompt = prompt[:-len(suffix)]
+                if len(suffix) > 0:
+                    prompt = prompt[:-len(suffix)]
             else:
                 prefix = get_generation_prompt(renderer, impersonate=impersonate)[0]
                 if state['mode'] == 'chat' and not impersonate:

modules/gradio_hijack.py

@@ -0,0 +1,72 @@
+'''
+Copied from: https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14184
+'''
+
+import inspect
+import warnings
+from functools import wraps
+
+import gradio as gr
+
+
+class GradioDeprecationWarning(DeprecationWarning):
+    pass
+
+
+def repair(grclass):
+    if not getattr(grclass, 'EVENTS', None):
+        return
+
+    @wraps(grclass.__init__)
+    def __repaired_init__(self, *args, tooltip=None, source=None, original=grclass.__init__, **kwargs):
+        if source:
+            kwargs["sources"] = [source]
+
+        allowed_kwargs = inspect.signature(original).parameters
+        fixed_kwargs = {}
+        for k, v in kwargs.items():
+            if k in allowed_kwargs:
+                fixed_kwargs[k] = v
+            else:
+                warnings.warn(f"unexpected argument for {grclass.__name__}: {k}", GradioDeprecationWarning, stacklevel=2)
+
+        original(self, *args, **fixed_kwargs)
+
+        self.webui_tooltip = tooltip
+
+        for event in self.EVENTS:
+            replaced_event = getattr(self, str(event))
+
+            def fun(*xargs, _js=None, replaced_event=replaced_event, **xkwargs):
+                if _js:
+                    xkwargs['js'] = _js
+
+                return replaced_event(*xargs, **xkwargs)
+
+            setattr(self, str(event), fun)
+
+    grclass.__init__ = __repaired_init__
+    grclass.update = gr.update
+
+
+for component in set(gr.components.__all__ + gr.layouts.__all__):
+    repair(getattr(gr, component, None))
+
+
+class Dependency(gr.events.Dependency):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+        def then(*xargs, _js=None, **xkwargs):
+            if _js:
+                xkwargs['js'] = _js
+
+            return original_then(*xargs, **xkwargs)
+
+        original_then = self.then
+        self.then = then
+
+
+gr.events.Dependency = Dependency
+
+gr.Box = gr.Group

modules/loaders.py

@@ -185,13 +185,9 @@ def transformers_samplers():
         'repetition_penalty_range',
         'encoder_repetition_penalty',
         'no_repeat_ngram_size',
-        'min_length',
         'seed',
         'do_sample',
         'penalty_alpha',
-        'num_beams',
-        'length_penalty',
-        'early_stopping',
         'mirostat_mode',
         'mirostat_tau',
         'mirostat_eta',
@@ -262,7 +258,6 @@ loaders_samplers = {
         'repetition_penalty_range',
         'encoder_repetition_penalty',
         'no_repeat_ngram_size',
-        'min_length',
         'seed',
         'do_sample',
         'mirostat_mode',
@@ -321,7 +316,6 @@ loaders_samplers = {
         'repetition_penalty_range',
         'encoder_repetition_penalty',
         'no_repeat_ngram_size',
-        'min_length',
         'seed',
         'do_sample',
         'mirostat_mode',

modules/presets.py

@@ -40,10 +40,6 @@ def default_preset():
         'do_sample': True,
         'encoder_repetition_penalty': 1,
         'no_repeat_ngram_size': 0,
-        'min_length': 0,
-        'num_beams': 1,
-        'length_penalty': 1,
-        'early_stopping': False,
         'sampler_priority': 'temperature\ndynamic_temperature\nquadratic_sampling\ntop_k\ntop_p\ntypical_p\nepsilon_cutoff\neta_cutoff\ntfs\ntop_a\nmin_p\nmirostat'
     }
 
@@ -52,7 +48,7 @@ def presets_params():
     return [k for k in default_preset()]
 
 
-def load_preset(name):
+def load_preset(name, verbose=False):
     generate_params = default_preset()
     if name not in ['None', None, '']:
         path = Path(f'presets/{name}.yaml')
@@ -65,6 +61,10 @@ def load_preset(name):
         else:
             logger.error(f"The preset \"{name}\" does not exist under \"{path}\". Using the default parameters.")
 
+    if verbose:
+        logger.info(f"\"{name}\" preset:")
+        pprint.PrettyPrinter(indent=4, width=1, sort_dicts=False).pprint(remove_defaults(generate_params))
+
     return generate_params
 
 
@@ -74,7 +74,7 @@ def load_preset_memoized(name):
 
 
 def load_preset_for_ui(name, state):
-    generate_params = load_preset(name)
+    generate_params = load_preset(name, verbose=True)
     state.update(generate_params)
     return state, *[generate_params[k] for k in presets_params()]
 

modules/shared.py

@@ -46,7 +46,6 @@ settings = {
     'truncation_length_min': 0,
     'truncation_length_max': 200000,
     'max_tokens_second': 0,
-    'max_updates_second': 0,
     'prompt_lookup_num_tokens': 0,
     'custom_stopping_strings': '',
     'custom_token_bans': '',

modules/text_generation.py

@@ -81,19 +81,16 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap
         state = copy.deepcopy(state)
         state['stream'] = True
 
-    min_update_interval = 0
-    if state.get('max_updates_second', 0) > 0:
-        min_update_interval = 1 / state['max_updates_second']
-
     # Generate
     for reply in generate_func(question, original_question, seed, state, stopping_strings, is_chat=is_chat):
         reply, stop_found = apply_stopping_strings(reply, all_stop_strings)
         if escape_html:
             reply = html.escape(reply)
+
         if is_stream:
             cur_time = time.time()
 
-            # Maximum number of tokens/second
+            # Limit number of tokens/second to make text readable in real time
             if state['max_tokens_second'] > 0:
                 diff = 1 / state['max_tokens_second'] - (cur_time - last_update)
                 if diff > 0:
@@ -101,13 +98,8 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap
 
                 last_update = time.time()
                 yield reply
-
-            # Limit updates to avoid lag in the Gradio UI
-            # API updates are not limited
             else:
-                if cur_time - last_update > min_update_interval:
+                yield reply
-                    last_update = cur_time
-                    yield reply
 
         if stop_found or (state['max_tokens_second'] > 0 and shared.stop_everything):
             break
@@ -287,7 +279,7 @@ def get_reply_from_output_ids(output_ids, state=None, starting_from=0):
 
 def generate_reply_HF(question, original_question, seed, state, stopping_strings=None, is_chat=False):
     generate_params = {}
-    for k in ['max_new_tokens', 'temperature', 'temperature_last', 'dynamic_temperature', 'dynatemp_low', 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', 'smoothing_curve', 'top_p', 'min_p', 'top_k', 'repetition_penalty', 'presence_penalty', 'frequency_penalty', 'repetition_penalty_range', 'typical_p', 'tfs', 'top_a', 'guidance_scale', 'penalty_alpha', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta', 'do_sample', 'encoder_repetition_penalty', 'no_repeat_ngram_size', 'min_length', 'num_beams', 'length_penalty', 'early_stopping']:
+    for k in ['max_new_tokens', 'temperature', 'temperature_last', 'dynamic_temperature', 'dynatemp_low', 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', 'smoothing_curve', 'top_p', 'min_p', 'top_k', 'repetition_penalty', 'presence_penalty', 'frequency_penalty', 'repetition_penalty_range', 'typical_p', 'tfs', 'top_a', 'guidance_scale', 'penalty_alpha', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta', 'do_sample', 'encoder_repetition_penalty', 'no_repeat_ngram_size']:
         if k in state:
             generate_params[k] = state[k]
 

modules/ui.py

@@ -117,7 +117,6 @@ def list_interface_input_elements():
         'max_new_tokens',
         'auto_max_new_tokens',
         'max_tokens_second',
-        'max_updates_second',
         'prompt_lookup_num_tokens',
         'seed',
         'temperature',
@@ -140,12 +139,8 @@ def list_interface_input_elements():
         'repetition_penalty_range',
         'encoder_repetition_penalty',
         'no_repeat_ngram_size',
-        'min_length',
         'do_sample',
         'penalty_alpha',
-        'num_beams',
-        'length_penalty',
-        'early_stopping',
         'mirostat_mode',
         'mirostat_tau',
         'mirostat_eta',

modules/ui_chat.py

@@ -181,7 +181,7 @@ def create_event_handlers():
         chat.generate_chat_reply_wrapper, gradio(inputs), gradio('display', 'history'), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         chat.save_history, gradio('history', 'unique_id', 'character_menu', 'mode'), None).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['textbox'].submit(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
@@ -189,28 +189,28 @@ def create_event_handlers():
         chat.generate_chat_reply_wrapper, gradio(inputs), gradio('display', 'history'), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         chat.save_history, gradio('history', 'unique_id', 'character_menu', 'mode'), None).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['Regenerate'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         partial(chat.generate_chat_reply_wrapper, regenerate=True), gradio(inputs), gradio('display', 'history'), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         chat.save_history, gradio('history', 'unique_id', 'character_menu', 'mode'), None).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['Continue'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         partial(chat.generate_chat_reply_wrapper, _continue=True), gradio(inputs), gradio('display', 'history'), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         chat.save_history, gradio('history', 'unique_id', 'character_menu', 'mode'), None).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['Impersonate'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         lambda x: x, gradio('textbox'), gradio('Chat input'), show_progress=False).then(
         chat.impersonate_wrapper, gradio(inputs), gradio('textbox', 'display'), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['Replace last reply'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
@@ -288,7 +288,7 @@ def create_event_handlers():
         chat.redraw_html, gradio(reload_arr), gradio('display')).then(
         lambda x: gr.update(choices=(histories := chat.find_all_histories(x)), value=histories[0]), gradio('interface_state'), gradio('unique_id')).then(
         chat.save_history, gradio('history', 'unique_id', 'character_menu', 'mode'), None).then(
-        lambda: None, None, None, _js=f'() => {{{ui.switch_tabs_js}; switch_to_chat()}}')
+        lambda: None, None, None, js=f'() => {{{ui.switch_tabs_js}; switch_to_chat()}}')
 
     shared.gradio['character_menu'].change(
         chat.load_character, gradio('character_menu', 'name1', 'name2'), gradio('name1', 'name2', 'character_picture', 'greeting', 'context')).success(
@@ -296,7 +296,7 @@ def create_event_handlers():
         chat.load_latest_history, gradio('interface_state'), gradio('history')).then(
         chat.redraw_html, gradio(reload_arr), gradio('display')).then(
         lambda x: gr.update(choices=(histories := chat.find_all_histories(x)), value=histories[0]), gradio('interface_state'), gradio('unique_id')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.update_big_picture_js}; updateBigPicture()}}')
+        lambda: None, None, None, js=f'() => {{{ui.update_big_picture_js}; updateBigPicture()}}')
 
     shared.gradio['mode'].change(
         lambda x: [gr.update(visible=x != 'instruct'), gr.update(visible=x == 'chat-instruct')], gradio('mode'), gradio('chat_style', 'chat-instruct_command'), show_progress=False).then(
@@ -332,15 +332,15 @@ def create_event_handlers():
 
     shared.gradio['save_chat_history'].click(
         lambda x: json.dumps(x, indent=4), gradio('history'), gradio('temporary_text')).then(
-        None, gradio('temporary_text', 'character_menu', 'mode'), None, _js=f'(hist, char, mode) => {{{ui.save_files_js}; saveHistory(hist, char, mode)}}')
+        None, gradio('temporary_text', 'character_menu', 'mode'), None, js=f'(hist, char, mode) => {{{ui.save_files_js}; saveHistory(hist, char, mode)}}')
 
     shared.gradio['Submit character'].click(
         chat.upload_character, gradio('upload_json', 'upload_img_bot'), gradio('character_menu')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.switch_tabs_js}; switch_to_character()}}')
+        lambda: None, None, None, js=f'() => {{{ui.switch_tabs_js}; switch_to_character()}}')
 
     shared.gradio['Submit tavern character'].click(
         chat.upload_tavern_character, gradio('upload_img_tavern', 'tavern_json'), gradio('character_menu')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.switch_tabs_js}; switch_to_character()}}')
+        lambda: None, None, None, js=f'() => {{{ui.switch_tabs_js}; switch_to_character()}}')
 
     shared.gradio['upload_json'].upload(lambda: gr.update(interactive=True), None, gradio('Submit character'))
     shared.gradio['upload_json'].clear(lambda: gr.update(interactive=False), None, gradio('Submit character'))
@@ -354,28 +354,28 @@ def create_event_handlers():
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         lambda x: x.update({'mode': 'instruct', 'history': {'internal': [], 'visible': []}}), gradio('interface_state'), None).then(
         partial(chat.generate_chat_prompt, 'Input'), gradio('interface_state'), gradio('textbox-default')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.switch_tabs_js}; switch_to_default()}}')
+        lambda: None, None, None, js=f'() => {{{ui.switch_tabs_js}; switch_to_default()}}')
 
     shared.gradio['send_instruction_to_notebook'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         lambda x: x.update({'mode': 'instruct', 'history': {'internal': [], 'visible': []}}), gradio('interface_state'), None).then(
         partial(chat.generate_chat_prompt, 'Input'), gradio('interface_state'), gradio('textbox-notebook')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.switch_tabs_js}; switch_to_notebook()}}')
+        lambda: None, None, None, js=f'() => {{{ui.switch_tabs_js}; switch_to_notebook()}}')
 
     shared.gradio['send_instruction_to_negative_prompt'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         lambda x: x.update({'mode': 'instruct', 'history': {'internal': [], 'visible': []}}), gradio('interface_state'), None).then(
         partial(chat.generate_chat_prompt, 'Input'), gradio('interface_state'), gradio('negative_prompt')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.switch_tabs_js}; switch_to_generation_parameters()}}')
+        lambda: None, None, None, js=f'() => {{{ui.switch_tabs_js}; switch_to_generation_parameters()}}')
 
     shared.gradio['send-chat-to-default'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         partial(chat.generate_chat_prompt, '', _continue=True), gradio('interface_state'), gradio('textbox-default')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.switch_tabs_js}; switch_to_default()}}')
+        lambda: None, None, None, js=f'() => {{{ui.switch_tabs_js}; switch_to_default()}}')
 
     shared.gradio['send-chat-to-notebook'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         partial(chat.generate_chat_prompt, '', _continue=True), gradio('interface_state'), gradio('textbox-notebook')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.switch_tabs_js}; switch_to_notebook()}}')
+        lambda: None, None, None, js=f'() => {{{ui.switch_tabs_js}; switch_to_notebook()}}')
 
-    shared.gradio['show_controls'].change(None, gradio('show_controls'), None, _js=f'(x) => {{{ui.show_controls_js}; toggle_controls(x)}}')
+    shared.gradio['show_controls'].change(None, gradio('show_controls'), None, js=f'(x) => {{{ui.show_controls_js}; toggle_controls(x)}}')

modules/ui_default.py

@@ -67,21 +67,21 @@ def create_event_handlers():
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         generate_reply_wrapper, gradio(inputs), gradio(outputs), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['textbox-default'].submit(
         lambda x: x, gradio('textbox-default'), gradio('last_input-default')).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         generate_reply_wrapper, gradio(inputs), gradio(outputs), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['markdown_render-default'].click(lambda x: x, gradio('output_textbox'), gradio('markdown-default'), queue=False)
     shared.gradio['Continue-default'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         generate_reply_wrapper, [shared.gradio['output_textbox']] + gradio(inputs)[1:], gradio(outputs), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['Stop-default'].click(stop_everything_event, None, None, queue=False)
     shared.gradio['prompt_menu-default'].change(load_prompt, gradio('prompt_menu-default'), gradio('textbox-default'), show_progress=False)

modules/ui_model_menu.py

@@ -75,7 +75,7 @@ def create_ui():
         with gr.Row():
             with gr.Column():
                 shared.gradio['loader'] = gr.Dropdown(label="Model loader", choices=loaders.loaders_and_params.keys(), value=None)
-                with gr.Box():
+                with gr.Blocks():
                     with gr.Row():
                         with gr.Column():
                             with gr.Blocks():

modules/ui_notebook.py

@@ -67,14 +67,14 @@ def create_event_handlers():
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         generate_reply_wrapper, gradio(inputs), gradio(outputs), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['textbox-notebook'].submit(
         lambda x: x, gradio('textbox-notebook'), gradio('last_input-notebook')).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         generate_reply_wrapper, gradio(inputs), gradio(outputs), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['Undo'].click(lambda x: x, gradio('last_input-notebook'), gradio('textbox-notebook'), show_progress=False)
     shared.gradio['markdown_render-notebook'].click(lambda x: x, gradio('textbox-notebook'), gradio('markdown-notebook'), queue=False)
@@ -83,7 +83,7 @@ def create_event_handlers():
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         generate_reply_wrapper, gradio(inputs), gradio(outputs), show_progress=False).then(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
-        lambda: None, None, None, _js=f'() => {{{ui.audio_notification_js}}}')
+        lambda: None, None, None, js=f'() => {{{ui.audio_notification_js}}}')
 
     shared.gradio['Stop-notebook'].click(stop_everything_event, None, None, queue=False)
     shared.gradio['prompt_menu-notebook'].change(load_prompt, gradio('prompt_menu-notebook'), gradio('textbox-notebook'), show_progress=False)

modules/ui_parameters.py

@@ -30,25 +30,48 @@ def create_ui(default_preset):
                             shared.gradio['max_new_tokens'] = gr.Slider(minimum=shared.settings['max_new_tokens_min'], maximum=shared.settings['max_new_tokens_max'], step=1, label='max_new_tokens', value=shared.settings['max_new_tokens'])
                             shared.gradio['temperature'] = gr.Slider(0.01, 5, value=generate_params['temperature'], step=0.01, label='temperature')
                             shared.gradio['top_p'] = gr.Slider(0.0, 1.0, value=generate_params['top_p'], step=0.01, label='top_p')
-                            shared.gradio['min_p'] = gr.Slider(0.0, 1.0, value=generate_params['min_p'], step=0.01, label='min_p')
                             shared.gradio['top_k'] = gr.Slider(0, 200, value=generate_params['top_k'], step=1, label='top_k')
-                            shared.gradio['repetition_penalty'] = gr.Slider(1.0, 1.5, value=generate_params['repetition_penalty'], step=0.01, label='repetition_penalty')
-                            shared.gradio['presence_penalty'] = gr.Slider(0, 2, value=generate_params['presence_penalty'], step=0.05, label='presence_penalty')
-                            shared.gradio['frequency_penalty'] = gr.Slider(0, 2, value=generate_params['frequency_penalty'], step=0.05, label='frequency_penalty')
-                            shared.gradio['repetition_penalty_range'] = gr.Slider(0, 4096, step=64, value=generate_params['repetition_penalty_range'], label='repetition_penalty_range')
                             shared.gradio['typical_p'] = gr.Slider(0.0, 1.0, value=generate_params['typical_p'], step=0.01, label='typical_p')
-                            shared.gradio['tfs'] = gr.Slider(0.0, 1.0, value=generate_params['tfs'], step=0.01, label='tfs')
+                            shared.gradio['repetition_penalty'] = gr.Slider(1.0, 1.5, value=generate_params['repetition_penalty'], step=0.01, label='repetition_penalty')
-                            shared.gradio['top_a'] = gr.Slider(0.0, 1.0, value=generate_params['top_a'], step=0.01, label='top_a')
+                            shared.gradio['frequency_penalty'] = gr.Slider(0, 2, value=generate_params['frequency_penalty'], step=0.05, label='frequency_penalty')
-                            shared.gradio['epsilon_cutoff'] = gr.Slider(0, 9, value=generate_params['epsilon_cutoff'], step=0.01, label='epsilon_cutoff')
+                            shared.gradio['presence_penalty'] = gr.Slider(0, 2, value=generate_params['presence_penalty'], step=0.05, label='presence_penalty')
-                            shared.gradio['eta_cutoff'] = gr.Slider(0, 20, value=generate_params['eta_cutoff'], step=0.01, label='eta_cutoff')
+                            shared.gradio['repetition_penalty_range'] = gr.Slider(0, 4096, step=64, value=generate_params['repetition_penalty_range'], label='repetition_penalty_range')
+                            shared.gradio['do_sample'] = gr.Checkbox(value=generate_params['do_sample'], label='do_sample')
+                            gr.Markdown("[Learn more](https://github.com/oobabooga/text-generation-webui/wiki/03-%E2%80%90-Parameters-Tab)")
 
                         with gr.Column():
+                            with gr.Group():
+                                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.')
+                                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['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['negative_prompt'] = gr.Textbox(value=shared.settings['negative_prompt'], label='Negative prompt', lines=3, elem_classes=['add_scrollbar'])
-                            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['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['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['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')
+
+                with gr.Column():
+                    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'])
+
+                    with gr.Row():
+                        with gr.Column():
+                            shared.gradio['min_p'] = gr.Slider(0.0, 1.0, value=generate_params['min_p'], step=0.01, label='min_p')
+                            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['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['dynamic_temperature'] = gr.Checkbox(value=generate_params['dynamic_temperature'], label='dynamic_temperature')
@@ -56,47 +79,16 @@ def create_ui(default_preset):
                             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['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=generate_params['do_sample'], label='do_sample')
+                            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.')
-                            shared.gradio['seed'] = gr.Number(value=shared.settings['seed'], label='Seed (-1 for random)')
-                            with gr.Accordion('Other parameters', open=False):
-                                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['min_length'] = gr.Slider(0, 2000, step=1, value=generate_params['min_length'], label='min_length')
-                                shared.gradio['num_beams'] = gr.Slider(1, 20, step=1, value=generate_params['num_beams'], label='num_beams', info='For Beam Search, along with length_penalty and early_stopping.')
-                                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')
 
-                    gr.Markdown("[Learn more](https://github.com/oobabooga/text-generation-webui/wiki/03-%E2%80%90-Parameters-Tab)")
-
-                with gr.Column():
-                    with gr.Row():
                         with gr.Column():
                             shared.gradio['truncation_length'] = gr.Slider(value=get_truncation_length(), minimum=shared.settings['truncation_length_min'], maximum=shared.settings['truncation_length_max'], step=256, label='Truncate the prompt up to this length', info='The leftmost tokens are removed if the prompt exceeds this length. Most models require this to be at most 2048.')
-                            shared.gradio['max_tokens_second'] = gr.Slider(value=shared.settings['max_tokens_second'], minimum=0, maximum=20, step=1, label='Maximum tokens/second', info='To make text readable in real time.')
-                            shared.gradio['max_updates_second'] = gr.Slider(value=shared.settings['max_updates_second'], minimum=0, maximum=24, step=1, label='Maximum UI updates/second', info='Set this if you experience lag in the UI during streaming.')
                             shared.gradio['prompt_lookup_num_tokens'] = gr.Slider(value=shared.settings['prompt_lookup_num_tokens'], minimum=0, maximum=10, step=1, label='prompt_lookup_num_tokens', info='Activates Prompt Lookup Decoding.')
-
+                            shared.gradio['max_tokens_second'] = gr.Slider(value=shared.settings['max_tokens_second'], minimum=0, maximum=20, step=1, label='Maximum tokens/second', info='To make text readable in real time.')
-                            shared.gradio['custom_stopping_strings'] = gr.Textbox(lines=2, value=shared.settings["custom_stopping_strings"] or None, label='Custom stopping strings', info='In addition to the defaults. Written between "" and separated by commas.', placeholder='"\\n", "\\nYou:"')
+                            shared.gradio['seed'] = gr.Number(value=shared.settings['seed'], label='Seed (-1 for random)')
-                            shared.gradio['custom_token_bans'] = gr.Textbox(value=shared.settings['custom_token_bans'] or None, label='Custom token bans', info='Specific token IDs to ban from generating, comma-separated. The IDs can be found in the Default or Notebook tab.')
-
-                        with gr.Column():
-                            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.')
                             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=shared.settings['stream'], label='Activate text streaming')
 
-                            with gr.Blocks():
-                                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.')
-
-                            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'])
-
         ui_chat.create_chat_settings_ui()
 
 

modules/ui_session.py

@@ -32,10 +32,10 @@ def create_ui():
         # Reset interface event
         shared.gradio['reset_interface'].click(
             set_interface_arguments, gradio('extensions_menu', 'bool_menu'), None).then(
-            lambda: None, None, None, _js='() => {document.body.innerHTML=\'<h1 style="font-family:monospace;padding-top:20%;margin:0;height:100vh;color:lightgray;text-align:center;background:var(--body-background-fill)">Reloading...</h1>\'; setTimeout(function(){location.reload()},2500); return []}')
+            lambda: None, None, None, js='() => {document.body.innerHTML=\'<h1 style="font-family:monospace;padding-top:20%;margin:0;height:100vh;color:lightgray;text-align:center;background:var(--body-background-fill)">Reloading...</h1>\'; setTimeout(function(){location.reload()},2500); return []}')
 
         shared.gradio['toggle_dark_mode'].click(
-            lambda: None, None, None, _js='() => {document.getElementsByTagName("body")[0].classList.toggle("dark")}').then(
+            lambda: None, None, None, js='() => {document.getElementsByTagName("body")[0].classList.toggle("dark")}').then(
             lambda x: 'dark' if x == 'light' else 'light', gradio('theme_state'), gradio('theme_state'))
 
         shared.gradio['save_settings'].click(

requirements.txt

@@ -1,10 +1,10 @@
 accelerate==0.27.*
-aqlm[gpu,cpu]==1.1.0; platform_system == "Linux"
+aqlm[gpu,cpu]==1.1.2; platform_system == "Linux"
 bitsandbytes==0.43.*
 colorama
 datasets
 einops
-gradio==3.50.*
+gradio==4.23.*
 hqq==0.1.5
 jinja2==3.1.2
 lm_eval==0.3.0
@@ -22,7 +22,7 @@ safetensors==0.4.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.38.*
+transformers==4.39.*
 tqdm
 wandb
 

requirements_amd.txt

@@ -2,7 +2,7 @@ accelerate==0.27.*
 colorama
 datasets
 einops
-gradio==3.50.*
+gradio==4.23.*
 hqq==0.1.5
 jinja2==3.1.2
 lm_eval==0.3.0
@@ -20,7 +20,7 @@ safetensors==0.4.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.38.*
+transformers==4.39.*
 tqdm
 wandb
 

requirements_amd_noavx2.txt

@@ -2,7 +2,7 @@ accelerate==0.27.*
 colorama
 datasets
 einops
-gradio==3.50.*
+gradio==4.23.*
 hqq==0.1.5
 jinja2==3.1.2
 lm_eval==0.3.0
@@ -20,7 +20,7 @@ safetensors==0.4.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.38.*
+transformers==4.39.*
 tqdm
 wandb
 

requirements_apple_intel.txt

@@ -2,7 +2,7 @@ accelerate==0.27.*
 colorama
 datasets
 einops
-gradio==3.50.*
+gradio==4.23.*
 hqq==0.1.5
 jinja2==3.1.2
 lm_eval==0.3.0
@@ -20,7 +20,7 @@ safetensors==0.4.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.38.*
+transformers==4.39.*
 tqdm
 wandb
 

requirements_apple_silicon.txt

@@ -2,7 +2,7 @@ accelerate==0.27.*
 colorama
 datasets
 einops
-gradio==3.50.*
+gradio==4.23.*
 hqq==0.1.5
 jinja2==3.1.2
 lm_eval==0.3.0
@@ -20,7 +20,7 @@ safetensors==0.4.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.38.*
+transformers==4.39.*
 tqdm
 wandb
 

requirements_cpu_only.txt

@@ -2,7 +2,7 @@ accelerate==0.27.*
 colorama
 datasets
 einops
-gradio==3.50.*
+gradio==4.23.*
 hqq==0.1.5
 jinja2==3.1.2
 lm_eval==0.3.0
@@ -20,7 +20,7 @@ safetensors==0.4.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.38.*
+transformers==4.39.*
 tqdm
 wandb
 

requirements_cpu_only_noavx2.txt

@@ -2,7 +2,7 @@ accelerate==0.27.*
 colorama
 datasets
 einops
-gradio==3.50.*
+gradio==4.23.*
 hqq==0.1.5
 jinja2==3.1.2
 lm_eval==0.3.0
@@ -20,7 +20,7 @@ safetensors==0.4.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.38.*
+transformers==4.39.*
 tqdm
 wandb
 

requirements_noavx2.txt

@@ -1,10 +1,10 @@
 accelerate==0.27.*
-aqlm[gpu,cpu]==1.1.0; platform_system == "Linux"
+aqlm[gpu,cpu]==1.1.2; platform_system == "Linux"
 bitsandbytes==0.43.*
 colorama
 datasets
 einops
-gradio==3.50.*
+gradio==4.23.*
 hqq==0.1.5
 jinja2==3.1.2
 lm_eval==0.3.0
@@ -22,7 +22,7 @@ safetensors==0.4.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.38.*
+transformers==4.39.*
 tqdm
 wandb
 

requirements_nowheels.txt

@@ -2,7 +2,7 @@ accelerate==0.27.*
 colorama
 datasets
 einops
-gradio==3.50.*
+gradio==4.23.*
 hqq==0.1.5
 jinja2==3.1.2
 lm_eval==0.3.0
@@ -20,7 +20,7 @@ safetensors==0.4.*
 scipy
 sentencepiece
 tensorboard
-transformers==4.38.*
+transformers==4.39.*
 tqdm
 wandb
 

server.py

@@ -18,6 +18,7 @@ warnings.filterwarnings('ignore', category=UserWarning, message='The value passe
 warnings.filterwarnings('ignore', category=UserWarning, message='Field "model_names" has conflict')
 
 with RequestBlocker():
+    from modules import gradio_hijack
     import gradio as gr
 
 import matplotlib
@@ -145,11 +146,9 @@ def create_interface():
         ui_model_menu.create_event_handlers()
 
         # Interface launch events
-        if shared.settings['dark_theme']:
+        shared.gradio['interface'].load(lambda: None, None, None, js=f"() => {{if ({str(shared.settings['dark_theme']).lower()}) {{ document.getElementsByTagName('body')[0].classList.add('dark'); }} }}")
-            shared.gradio['interface'].load(lambda: None, None, None, _js="() => document.getElementsByTagName('body')[0].classList.add('dark')")
+        shared.gradio['interface'].load(lambda: None, None, None, js=f"() => {{{js}}}")
-
+        shared.gradio['interface'].load(lambda x: None, gradio('show_controls'), None, js=f'(x) => {{{ui.show_controls_js}; toggle_controls(x)}}')
-        shared.gradio['interface'].load(lambda: None, None, None, _js=f"() => {{{js}}}")
-        shared.gradio['interface'].load(None, gradio('show_controls'), None, _js=f'(x) => {{{ui.show_controls_js}; toggle_controls(x)}}')
         shared.gradio['interface'].load(partial(ui.apply_interface_values, {}, use_persistent=True), None, gradio(ui.list_interface_input_elements()), show_progress=False)
         shared.gradio['interface'].load(chat.redraw_html, gradio(ui_chat.reload_arr), gradio('display'))
 
@@ -157,9 +156,10 @@ def create_interface():
         extensions_module.create_extensions_block()  # Extensions block
 
     # Launch the interface
-    shared.gradio['interface'].queue(concurrency_count=64)
+    shared.gradio['interface'].queue()
     with OpenMonkeyPatch():
         shared.gradio['interface'].launch(
+            max_threads=64,
             prevent_thread_lock=True,
             share=shared.args.share,
             server_name=None if not shared.args.listen else (shared.args.listen_host or '0.0.0.0'),
@@ -168,7 +168,8 @@ def create_interface():
             auth=auth or None,
             ssl_verify=False if (shared.args.ssl_keyfile or shared.args.ssl_certfile) else True,
             ssl_keyfile=shared.args.ssl_keyfile,
-            ssl_certfile=shared.args.ssl_certfile
+            ssl_certfile=shared.args.ssl_certfile,
+            allowed_paths=["cache", "css", "extensions", "js"]
         )
 
 

settings-template.yaml

@@ -15,7 +15,6 @@ truncation_length: 2048
 truncation_length_min: 0
 truncation_length_max: 200000
 max_tokens_second: 0
-max_updates_second: 0
 prompt_lookup_num_tokens: 0
 custom_stopping_strings: ''
 custom_token_bans: ''