Spaces:

---

huggingchat

/

chat-ui

like 1.12k

Running

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

I'm seeing these "<|im_end|>" on meta-llama/Llama-3.3-70B-Instruct occasionally now.

i just saw it

could you try it now ? should be better

TYSM! anyway we just managed to find the latest linux mint and ubuntu version after your fix.

btw, would it be better if you can replace nvidia's nemotron model with google's gemma3-27b and replace microsoft's phi3.5 with phi-4-instruct?
and please don't hesitate to include support community tools on all newly updated models (including deepseek r1-distilled-qwen-32b, qwq-32b, and possibly phi-4 and even gemma-3-27b,..... as well).

Any plans on replacing Command R+ with Command-A?

dammit................... deepseek-r1-distilled-32b hallucinated again?!

I have a quick question about LLM hallucinations: how can we ensure that the models have good access to internet? For example, when I tried to look at a certain (medical) with a url provided to llama, it returned completely unrelated content.

Any plans on replacing Command R+ with Command-A?

If it's completely uncensored like command R+ & better reasoning (not chain of thought time consuming thing) it'd be superb!
We need a very good uncensored model with high level reasoning. Hermes 3 70B should've been a part in this roaster too, but idk why not.

Hi everyone! We just released Gemma 3 27B on HuggingChat 🚀

Try it out here: https://huggingface.co/chat/models/google/gemma-3-27b-it

Let us know if it works well for you!