You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
I reviewed the Discussions, and have a new and useful enhancement to share.
Feature Description
Currently, the Llama.cpp web UI does not let you type at all in the chat textarea during generation, which the previous version of the web UI lets you do. This feature request is to allow users to type in the textbox again in the new UI.
When the model is generating, if you press enter, it should:
Stop the model from generating
Insert your new message at the end of the current conversation
Start generation again
Motivation
When you are running large models that don't output quickly, it is nice to draft your response before the model is finished generating. Sometimes I think about my response while it's still going, and I don't want it to end early.
Anyway, this also was the prior behaviour, so it should be restored.
Possible Implementation
This at least stops the textarea from being disabled:
diff --git a/examples/server/webui/index.html b/examples/server/webui/index.html
index d3893ea4..17609820 100644
--- a/examples/server/webui/index.html+++ b/examples/server/webui/index.html@@ -153,9 +153,8 @@
class="textarea textarea-bordered w-full"
placeholder="Type a message (Shift+Enter to add a new line)"
v-model="inputMsg"
- @keydown.enter.exact.prevent="sendMessage"+ @keydown.enter.exact.prevent="isGenerating && stopGeneration(); sendMessage()"
@keydown.enter.shift.exact.prevent="inputMsg += '\n'"
- :disabled="isGenerating"
id="msg-input"
dir="auto"
></textarea>
But if you press Enter during generation, it puts your message out of order and does not resume generation:
(Nothing more is generated and it's the user's turn again according to the UI.)
So, I would like some help from someone familiar with the web UI.
The text was updated successfully, but these errors were encountered:
Prerequisites
Feature Description
Currently, the Llama.cpp web UI does not let you type at all in the chat textarea during generation, which the previous version of the web UI lets you do. This feature request is to allow users to type in the textbox again in the new UI.
When the model is generating, if you press enter, it should:
Motivation
When you are running large models that don't output quickly, it is nice to draft your response before the model is finished generating. Sometimes I think about my response while it's still going, and I don't want it to end early.
Anyway, this also was the prior behaviour, so it should be restored.
Possible Implementation
This at least stops the textarea from being disabled:
But if you press Enter during generation, it puts your message out of order and does not resume generation:
(Nothing more is generated and it's the user's turn again according to the UI.)
So, I would like some help from someone familiar with the web UI.
The text was updated successfully, but these errors were encountered: