Spaces:
Running
[MODELS] Discussion
Here we can discuss about HuggingChat available models.
what are limits of using these? how many api calls can i send them per month?
How can I know which model am using
How can I know which model am using
at the bottom of your screen:
Out of all these models, Gemma, which was recently released, has the newest information about .NET. However, I don't know which one has the most accurate answers regarding coding
Gemma seems really biased. With web search on, it says that it doesn't have access to recent information asking it almost anything about recent events. But when I ask it about recent events with Google, I get responses with the recent events.
apparently gemma cannot code?
Gemma is just like Google's Gemini series models, it have a very strong moral limit put on, any operation that may related to file operation, access that might be deep, would be censored and refused to reply.
So even there are solution for such things in its training data, it will just be filtered and ignored.
But still didn't test the coding accuracy that doesn't related to these kind of "dangerous" operations
@NorbertKlau95683
We're currently looking at replacing Command-R-plus with Command-A. The hardware requirements are similar so that's not a problem, the main difference is the architecture is new (Cohere2ForCausalLM), so we first need to add support to TGI. There were a bunch of releases recently so the team is busy adding support to other models too. Once that's done we'll replace it in the API & HuggingChat!
Hi HuggingFace Team and @nsarrazin ,
I was wondering if it would be possible to replace the Command-R-plus model with the new Command-A model? Itโs surprisingly accurate at following prompts closely, has a big context space, and is incredibly creative - especially great for writing stories. I think it could be a fantastic addition to the platform.
Looking forward to your thoughts. Thanks.
You can use it on Cohere Chat until it's added to HuggingChat.
@nsarrazin gemma is not generating any output and it keeps processing , if possible can you help us out.
Thanks
Both Gemma and QwQ should be working well now! Let me know if you still have issues. @acharyaaditya26
Hi @nsarrazin still same problem it keep processing but not generating any output.
Hi guys there are this many models currently available on chat-ui platform, wouldn't it be good if some models are removed like phi3.5, mistral-nemo , Hermes and llama-vision-instruct, deepseek-qwen32b-distilled etc. which will free up GPU's and make space for new and improve models like gemma, qwq, cohere-a etc. Just a thought
mine also stuck w/ same problem in gemma 3
anyway thanks @nsarrazin for fixing overloads in qwq-32b! thanks for your help we can now solve difficult math problems with deepseek-r1 + qwq32b !.
btw, wouldn't it be better if the devs can allow users to customize search engines in the settings config to enforce the model to search using the search engine as chosen by the user? hope the devs will take this as a great solution
i need qvq in huggingchat