mradermacher

/

model_requests

like 90

https://github.com/ggml-org/llama.cpp/pull/13021

Thanks for the heads-up. I've queued the models we hadn't queued before, and will push them once we have a new build.

nico pointed out that the glm 414 model is still broken: https://github.com/ggml-org/llama.cpp/pull/13099

should work now

@WesPro What makes you think so? The continuation of https://github.com/ggml-org/llama.cpp/pull/13099 is still open under https://github.com/ggml-org/llama.cpp/pull/13140.

https://github.com/ggml-org/llama.cpp/pull/13140 just got merged so this is now finally fixed. @mradermacher Please update to the latest version of our llama.cpp fork and resume all GLM based models.

Finally :) They are all on their way. conversion was fine, imatrix in the queue.