Add a simple tokenizer to the UI

css/main.css

@@ -120,7 +120,7 @@ div.svelte-15lo0d8 > *, div.svelte-15lo0d8 > .form > * {
 }
 
 .textbox_logits textarea {
-    height: calc(100dvh - 241px);
+    height: calc(100dvh - 232px);
 }
 
 .textbox_logits_notebook textarea {
@@ -131,8 +131,7 @@ div.svelte-15lo0d8 > *, div.svelte-15lo0d8 > .form > * {
 .textbox_default_output textarea,
 .textbox_logits textarea,
 .textbox_logits_notebook textarea,
-.textbox textarea
+.textbox textarea {
-{
     font-size: 16px !important;
     color: #46464A !important;
 }

modules/ui_default.py

@@ -3,6 +3,7 @@ import gradio as gr
 from modules import logits, shared, ui, utils
 from modules.prompts import count_tokens, load_prompt
 from modules.text_generation import (
+    encode,
     generate_reply_wrapper,
     stop_everything_event
 )
@@ -54,6 +55,10 @@ def create_ui():
                         shared.gradio['logits-default'] = gr.Textbox(lines=23, label='Output', elem_classes=['textbox_logits', 'add_scrollbar'])
                         shared.gradio['logits-default-previous'] = gr.Textbox(lines=23, label='Previous output', elem_classes=['textbox_logits', 'add_scrollbar'])
 
+                with gr.Tab('Tokens'):
+                    shared.gradio['get_tokens-default'] = gr.Button('Get token IDs for the input')
+                    shared.gradio['tokens-default'] = gr.Textbox(lines=23, label='Tokens', elem_classes=['textbox_logits', 'add_scrollbar'])
+
 
 def create_event_handlers():
     shared.gradio['Generate-default'].click(
@@ -94,3 +99,5 @@ def create_event_handlers():
     shared.gradio['get_logits-default'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         logits.get_next_logits, gradio('textbox-default', 'interface_state', 'use_samplers-default', 'logits-default'), gradio('logits-default', 'logits-default-previous'), show_progress=False)
+
+    shared.gradio['get_tokens-default'].click(lambda x : str(encode(x)[0].tolist()), gradio('textbox-default'), gradio('tokens-default'), show_progress=False)

modules/ui_notebook.py

@@ -3,6 +3,7 @@ import gradio as gr
 from modules import logits, shared, ui, utils
 from modules.prompts import count_tokens, load_prompt
 from modules.text_generation import (
+    encode,
     generate_reply_wrapper,
     stop_everything_event
 )
@@ -40,6 +41,10 @@ def create_ui():
                         shared.gradio['logits-notebook'] = gr.Textbox(lines=23, label='Output', elem_classes=['textbox_logits_notebook', 'add_scrollbar'])
                         shared.gradio['logits-notebook-previous'] = gr.Textbox(lines=23, label='Previous output', elem_classes=['textbox_logits_notebook', 'add_scrollbar'])
 
+                with gr.Tab('Tokens'):
+                    shared.gradio['get_tokens-notebook'] = gr.Button('Get token IDs for the input')
+                    shared.gradio['tokens-notebook'] = gr.Textbox(lines=23, label='Tokens', elem_classes=['textbox_logits_notebook', 'add_scrollbar'])
+
                 with gr.Row():
                     shared.gradio['Generate-notebook'] = gr.Button('Generate', variant='primary', elem_classes='small-button')
                     shared.gradio['Stop-notebook'] = gr.Button('Stop', elem_classes='small-button', elem_id='stop')
@@ -96,3 +101,5 @@ def create_event_handlers():
     shared.gradio['get_logits-notebook'].click(
         ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
         logits.get_next_logits, gradio('textbox-notebook', 'interface_state', 'use_samplers-notebook', 'logits-notebook'), gradio('logits-notebook', 'logits-notebook-previous'), show_progress=False)
+
+    shared.gradio['get_tokens-notebook'].click(lambda x : str(encode(x)[0].tolist()), gradio('textbox-notebook'), gradio('tokens-notebook'), show_progress=False)

modules/ui_parameters.py

@@ -118,7 +118,7 @@ def create_ui(default_preset):
                             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['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 a tokenizer.json file.')
+                                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.')
                                 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')