☎️ Talkie Instruct 13B
#2442
by redaihf - opened
https://huggingface.co/lewtun/talkie-1930-13b-it-hf
Llama.cpp will need to be updated first because support has only just been merged in.
Hey, sorry for delay, needed to update llama cpp =)
It's queued!
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#talkie-1930-13b-it-hf-GGUF for quants to appear.
I'm was so surprised that the TalkieForCausalLM architecture is supported by llama.cpp but it really is: https://github.com/ggml-org/llama.cpp/pull/22596
What an interesting model. I will give it my benchmark just for fun to see what happens. I'm sure it will answer certain questions very different compared to modern models.