mradermacher

/

model_requests

like 198

CISC merged commit 3733366 into ggml-org:master yesterday

let's hope we are new enough =)
if not, touch me again please =)

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#Ling-3.0-flash-GGUF for quants to appear.

let's hope we are new enough =)

Please don't hope and queue it on rich1. rich1 worked a whole night on this, preventing meaningful quantisation of other models, for a model that clearly isn't supported yet - nico last merged our llama.cpp with upstream on the 15th, I think, so this cannot be included. Manually queue it for nico1 - nico1 has disk bandwidth to spare in case we need to wait and restart.

Also, feel free to bug nico. once he has merged it, our binaries usually get updated the next time i queue models.

sigh :)

Also, feel free to bug nico.

yes, I do that every day all day =)

nico last merged our llama.cpp with upstream on the 15th

I queued with llama nico, not main llama, so wasnt sure exactly about the date

but yeah, bad decision with size of model =(

yes, I do that every day all day =)

I updated llame.cpp 5 hours ago when you asked me to and just updated it again.

I queued with llama nico, not main llama, so wasnt sure exactly about the date

llama nico can't ever be more recent than the most recent version of our fork and unless you run the update script before queueing it might even be more outdated than mradermacher's version as llama nico is getting updated on demand meaning I only update it when there is a request that requires the latest version.

I now queued it to nico with using the just updated llama nico. :D

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#Ling-3.0-flash-GGUF for quants to appear.