Tencent just released a new open-source model called Hunyuan-A13B-Instruct. It has open weights (not sure about code), and it runs locally (well if...
For further actions, you may consider blocking this person and/or reporting abuse
Finally, I can ditch my $20 ChatGPT subscription!
we finally know the price of privacy, $4600 :D
Love seeing detailed hands-on guides for these new MoE models, especially the long context support out of the box. Have you noticed any quirks or strengths when running multi-step agent tasks compared to LLaMA or Mixtral?
This looks very interesting! I will have to give it a try but Iām GPU poor :(
Pls use my referral link so we both shall be a little bit less gpu poor
Love the link to the PR in progress
That helped a lot to see other people trying to get it to run as well :D
For the validation or for the peer input?