diff --git a/docs/models.md b/docs/models.md
index c45030f..2d5e0d7 100644
--- a/docs/models.md
+++ b/docs/models.md
@@ -33,6 +33,16 @@ This script implements the core underlying model for VALL-E. This handle:
 
 This script aims to implement everything as required per VALL-E agnostically, to allow for different implementations to contain little extra code.
 
+### Tasks
+
+The base model handles processing inputs into token sequences, per the requested task assigned to each input in a batch.
+
+Most sequences follow a `<text><RVQ level><language><prompt><output>` sequence, but some tasks will receive the prompt as a list of tensors, instead.
+
+The length predictor `len` task will naively output the length in base-10 followed by a stop token.
+
+Speech-To-Text will follow a reverse sequence of `<audio><language><RVQ level><output>`.
+
 ## `models/ar_nar.py`
 
 This script implements VALL-E as a unified autoregressive and non-autoregressive model, where RVQ-level 0 is inferenced autoregressively, the remaining levels are infereneced non-autoregressively.
diff --git a/vall_e/webui.py b/vall_e/webui.py
index b81c706..2a1f4c8 100644
--- a/vall_e/webui.py
+++ b/vall_e/webui.py
@@ -402,8 +402,6 @@ with ui:
 							layout["inference_tts"]["inputs"]["ar-temp"] = gr.Slider(value=0.5, minimum=0.0, maximum=1.5, step=0.05, label="Temperature (AR)", info="Modifies the randomness from the samples in the AR. (0 to greedy* sample)")
 							layout["inference_tts"]["inputs"]["nar-temp"] = gr.Slider(value=0.0, minimum=0.0, maximum=1.5, step=0.05, label="Temperature (NAR)", info="Modifies the randomness from the samples in the NAR. (0 to greedy sample)")
 						with gr.Row():
-							layout["inference_tts"]["inputs"]["layer-skip"] = gr.Checkbox(label="Layer Skip", info="Performs self-speculative early exit 'sampling'")
-							layout["inference_tts"]["inputs"]["refine-on-stop"] = gr.Checkbox(label="Refine on <stop>", info="Uses the last step's logits for the AR sequence instead.")
 							layout["inference_tts"]["inputs"]["language"] = gr.Dropdown(choices=get_languages(), label="Language", value="en")
 					with gr.Tab("Sampler Settings"):
 						with gr.Row():
@@ -432,6 +430,9 @@ with ui:
 							with gr.Row():
 								layout["inference_tts"]["inputs"]["dynamic-sampling"] = gr.Checkbox(label="Dynamic Temperature", info="Dynamically adjusts the temperature based on the highest confident predicted token per sampling step.")
 								layout["inference_tts"]["inputs"]["entropix-sampling"] = gr.Checkbox(label="Entropix Sampling", info="Dynamically samples based on entropy/varentropy values from the logits / attention scores.")
+							with gr.Row():
+								layout["inference_tts"]["inputs"]["layer-skip"] = gr.Checkbox(label="Layer Skip", info="Performs self-speculative early exit 'sampling'")
+								layout["inference_tts"]["inputs"]["refine-on-stop"] = gr.Checkbox(label="Refine on <stop>", info="Uses the last step's logits for the AR sequence instead.")
 							with gr.Row():
 								layout["inference_tts"]["inputs"]["layer-skip-exit-layer"] = gr.Slider(value=11, minimum=0, maximum=11, step=1, label="Layer Skip Exit Layer", info="Maximum model layer to exit early from.")
 								layout["inference_tts"]["inputs"]["layer-skip-entropy-threshold"] = gr.Slider(value=0.1, minimum=0, maximum=1.0, step=0.01, label="Layer Skip Entropy Threshold", info="Entropy threshold for early-exit")