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
qwq 332b is also overloaded for now, please fix this problem asap
Any plans on replacing Command R+ with Command-A?
yeah, we want this model to be replacing command r+!
plus we need to bring back the legendary hermes 3 70b!
qwq 332b is also overloaded for now, please fix this problem asap
Hi, this guys are providing best of open-source literally for free we all should be little bit kinder and not demanding they don't owe us anything . Your tone is little bit harsh.
Man how tf QVQ-72 used all of its token. So I was browsing in qwen's den (chat.qwen.ai) and I had this problem of physics, sent to the model and that freakin thing literally used to its fullest to answer the question, the funny thing is it didn't even finished the response because of out of token, lol. The reason i uploaded the image is because this type of math is tricky for ai model and probably you can use it to check if the model is good at math, again lol. Currently grok is fire in the ranking of itt(image-text-to-text) model, posted multiple math problem and it was always ahead of chatgpt and answered most of the question correctly, chatgpt has only the capability to ocr, it became trash in front of chinese brain (by that i meant qwen and i am sure if they get the same cluster elon has, they will definitely produce something mind blowing). So if someone is studying math, and has not yet used grok then use it man, you will be amazed for sure. BTW, anyone know why gemini is the worst of all, it is not built by some homemade engineer, straight from some of the world's sophisticated brain then why tf that model is kind of shit compared to 7B models. Seems like google is actually in the path to be shutdown one day.
qwq and gamma are overloaded, i need qvq in huggingchat and the math formulas which be in thinking mode especially -qwq- appear in latex and in other models but some works.
So, i hope you to solve all this problems.
me too, i want qwq and gemma to no longer have any hallucinations or overloads
This website is great and all, but can we get think token formatting for non CoT models?
I usually like to prompt engineer models to behave a bit like QwQ.
Hi there, can anyone fix this, qwq-32b did search the internet but took too long to respond.