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
will you add Llama 4 Behemoth ?
qwen 2.5 vl isn't work ???
what is HAPPENING HERE?!
CoHere on both it's dedicated space and HuggingChat have stopped replying altogether.
Cohere on HuggingChat just gives three loading dots and no longer responds. I have just tried other models as well on HuggingChat and they do give responses... but they are all just making the whole page freeze midway through response when you try and ask for some sort of story, which is not supposed to happen. (I tried asking both Gemini and Llama models a story in the Family Guy universe for inspiration of my own story, but they are giving same freezing result)
CoHere on both it's dedicated space and HuggingChat have stopped replying altogether.
Cohere on HuggingChat just gives three loading dots and no longer responds. I have just tried other models as well on HuggingChat and they do give responses... but they are all just making the whole page freeze midway through response when you try and ask for some sort of story, which is not supposed to happen. (I tried asking both Gemini and Llama models a story in the Family Guy universe for inspiration of my own story, but they are giving same freezing result)
we agree, we keep insisting on the cohere devs to add their command a model to huggingchat, but they were too reluctant to do so: https://huggingface.co/CohereLabs/c4ai-command-a-03-2025/discussions/14
in addition to that, please also consider adding two new models to huggingchat: deephermes-3-mistral-24b-preview and microsoft phi-4 reasoning plus. they have highly advanced reasoning capabilities and can perform on par with similar models like qwq 32b or qwen 3 30b a3b.
Here is the repo for these 2 models:
https://huggingface.co/NousResearch/DeepHermes-3-Mistral-24B-Preview
https://huggingface.co/microsoft/Phi-4-reasoning-plus
Whats the policy according to huggingface, will they collect my prompts, the inputs or the outputs
in the about & privacy section in huggingchat, it says
"We endorse Privacy by Design. As such, your conversations are private to you and will not be shared with anyone, including model authors, for any purpose, including for research or model training purposes.
You conversation data will only be stored to let you access past conversations. You can click on the Delete icon to delete any past conversation at any moment."
as long as this is still up to date (I'm not quite sure when it was last updated) it should be pretty correct.