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.
I am unable to delete any chats made that are current/newly created/recent/or old, doing this on every model too.
the problem is that the web search function is failing in many ai models, forcing us to try again.
we frequently experience this issue in qwen and deepseek models, the web search function llama and command r+ models work quite fine.
It's not really a problem, but I thought I'd report it anyway. When the search function is turned on, I think there are more cases where no search results are returned and the system infers that there are no search results.
Well, we can work around this by being creative with the prompts...
Maybe it's because Hugging Chat is searching with โโ...
It's not really a problem, but I thought I'd report it anyway. When the search function is turned on, I think there are more cases where no search results are returned and the system infers that there are no search results.
Well, we can work around this by being creative with the prompts...
Maybe it's because Hugging Chat is searching with โโ...
u absolutely nailed it my friend :))
hey! not sure if this is just me or not, but when I try to generate a new thing from the same prompt with Llama 70B and Quen 72B (haven't tested the others yet) it just gives me the same answer.
EDIT: it is NOT an issue with Cohere Command R, but it IS with Deepseek Distill Quen.
hey! not sure if this is just me or not, but when I try to generate a new thing from the same prompt with Llama 70B and Quen 72B (haven't tested the others yet) it just gives me the same answer.
EDIT: it is NOT an issue with Cohere Command R, but it IS with Deepseek Distill Quen.
Yep, the chatbot models do not work anymore, they have officially stopped generating new responses no matter what is typed or changed in prompts. And the people behind HuggingFace have stopped caring for the community. There is no more chatbots out there that are free to use and doesn't take up PC local storage. :(
I wouldn't say "stopped caring", I'm sure they're working hard on adding new stuff and fixing the issues. after all, the last update (according to the about section on huggingchat) was on the 14th of February this year.
also, it doesn't work when you change the prompts? I'm able to change them and get a new result just fine, I'm just getting the same result for the same prompt.
we need more people to help mr. sarrazin out, because he's all alone in project. plus he needs to take holidays like us do. and we have seen in the most recent changes to the chat-ui code, mr. sarrazin did it all by himself (alongside dependabot security updates). salute to mr. sarrazin for handling this extreme work.