Spaces:
Running
Your feedback on HuggingChat
Any constructive feedback is welcome here. Just use the "New Discussion" button! or this link.
^^ pin it? :)
HuggingChat can only speak poor Chinese. I told him, 'Let's speak in Chinese.' He said, 'Sure,' but then continued to speak in English or with incorrect pinyin. But this is an interesting project.
Vicuna is a great alternative to Open Assistant as it offers a more advanced and capable language model. Both are open-source solutions, allowing for customization and extension of their functionality. Vicuna's natural language processing capabilities are particularly impressive, making it a more intelligent virtual assistant overall.
Vicuna is a great alternative to Open Assistant as it offers a more advanced and capable language model. Both are open-source solutions, allowing for customization and extension of their functionality. Vicuna's natural language processing capabilities are particularly impressive, making it a more intelligent virtual assistant overall.
Yes, I answered your post ๐
this need more prompting than Google's bard or Chatgpt like they understand quickly what I need and also the feel that you are chatting with machine is still there
Sometimes there is no response. Most of the time it finishes half way or less through and answer. I am using it to program dotnet core.
The newest model in the CoHere space isn't listening to the prompts anymore; it's just giving very long responses that actually crash the browser being used.
I just asked it to create a story with a specific recommended word count, and it gave way more than it was given resulting in me force Restarting Firefox twice. I have a feeling it's gonna do it on another browser if I try another. The other models in the CoHere space don't crash out browsers at all or give very long responses at all
I agree with the post above.
HuggingChats UI, when generating, is surprisingly slow and ends up crashing by browser a lot, when longer texts are generated. Especially when writing code, it gets stuttery real fast, and it ends up completely halting the visual update. At that point my cursor doesn't highlight UI elements anymore, so it's time to restart the tab, if I can even do that still.
I'm assuming this is due to the markdown parser.
I have a similar issue on mobile as
@croque16
. When typing some message which expands the text box to fit more content and then send the message, it doesn't reset the size of the textbox container. It remains at the large size. One has to type in a character to reset the empty text field size.
The issue was discussed before in the Models section, but I believe this is the correct place for it.
The box to enter or input text keeps getting stuck as 'double tall' often blocking out the reload or copy buttons at the bottom of the AI latest output. Happening in chrome on both PC and mobile. Also those buttons need to be broken up and spaced out, too easy to misclick and hard to press on mobile.
When you want to send a prompt on Librewolf you can't send with just Enter.
The box to enter or input text keeps getting stuck as 'double tall' often blocking out the reload or copy buttons at the bottom of the AI latest output. Happening in chrome on both PC and mobile. Also those buttons need to be broken up and spaced out, too easy to misclick and hard to press on mobile.
This should be fixed can you confirm @Smorty100 ?
The box to enter or input text keeps getting stuck as 'double tall' often blocking out the reload or copy buttons at the bottom of the AI latest output. Happening in chrome on both PC and mobile. Also those buttons need to be broken up and spaced out, too easy to misclick and hard to press on mobile.
This should be fixed can you confirm @Smorty100 ?
:( not fixed on mobile chrome android
@victor It is not fixed yet.
Test results
After sending the first message the box is cleared and it keeps its size for half a second. Then it shows the actual chat interface starts generating and then the text box snaps back to the small size.
After that first message, every multiline prompt extends the message box and keeps it that way until another character is entered so that the box realizes that it should update it's size.