{"id":47928886,"user":"pizzalife","time":1777334878,"time_ago":"4 months ago","type":"comment","content":"

This is cool. Is it possible to easily install with ollama?","comments":[{"id":47930035,"user":"nateb2022","time":1777345326,"time_ago":"4 months ago","type":"comment","content":"

There's no GGUF available, but the process shouldn't be too hard from the provided .ckpt PyTorch checkpoint.","comments":[{"id":47946017,"user":"ranger_danger","time":1777454929,"time_ago":"4 months ago","type":"comment","content":"

There is one now: https://huggingface.co/dsv147/talkie-1930-13b-it-hf-gguf-Q4_...","comments":[{"id":47946355,"user":"dTal","time":1777458301,"time_ago":"4 months ago","type":"comment","content":"

404","comments":[{"id":47948747,"user":"ranger_danger","time":1777471960,"time_ago":"4 months ago","type":"comment","content":"

Looks like it was deleted, here is another https://huggingface.co/DJLougen/talkie-1930-13b-GGUF/tree/ma...

After downloading, it looks like it uses a custom "talkie" model architecture that is not supported at least by llama.cpp.

Edit: This one has now been deleted as well for some reason...","comments":[{"id":47969554,"user":"ranger_danger","time":1777591102,"time_ago":"4 months ago","type":"comment","content":"

Update: here is a patched llama.cpp and quantized model for desktop use: https://github.com/solwyc/talkie-1930-13b-it-q5","comments":[],"comments_count":0,"level":4,"url":"item?id=47969554"}],"comments_count":1,"level":3,"url":"item?id=47948747"}],"comments_count":2,"level":2,"url":"item?id=47946355"}],"comments_count":3,"level":1,"url":"item?id=47946017"}],"comments_count":4,"level":0,"url":"item?id=47930035"}],"comments_count":5,"url":"item?id=47928886"}

Comment by pizzalife