A new Qwen 32b merge
Why not? :-) can you quant it when you get a chance?
Oh my, I can queue it, but I won't do all those calculations myself, we have computers for that :) Anyway, queued, as usual.
Was this broken by any chance?
you mean it didn't show up, hmm...
It didn't mate and I tried another GGUF someone had kindly uploaded and it wouldn't load.
yes, seems conversion worked, but imatrix generation failed (likely tensor or tokenizer problem). sorry, for not reporting it. it's a wild ride atm.
No worries :-) No idea how I'll fix that.
I know that feeling :)
Try this if you can
Try this if you can
@DazzlingXeno Can you please rename it? I don't like the idea of having a model named "Test" on mradermacher. While surprisingly https://huggingface.co/mradermacher/Test-GGUF does not exist yet I feel like the name should be slightly more unique.
Try this if you can
@DazzlingXeno Can you please rename it? I don't like the idea of having a model named "Test" on mradermacher. While surprisingly https://huggingface.co/mradermacher/Test-GGUF does not exist yet I feel like the name should be slightly more unique.
Done.
@DazzlingXeno
Thanks for renaming! It's queued! :D
Let's hope for the best.
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#EVA-Instruct-R1-GGUF for quants to appear.