https://huggingface.co/helixdouble/GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint
You did a quantization for helixdouble's v1 before, but the abliteration wasn't quite effective. Here is the v2 version, which the author has updated and performs significantly better.
I really appreciate your help in advance!
It's queued, but it's quite a big model, so it might take a while as it went to the large model queue which is usually handled manually and a bit slow
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#GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint-GGUF for quants to appear.
It's queued, but it's quite a big model, so it might take a while as it went to the large model queue which is usually handled manually and a bit slow
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#GLM-5.1-FP8-Abliterated-v2-SoftRefusal-Research-Checkpoint-GGUF for quants to appear.
Hi! Just wanted to ask about the progress of the quantization. I saw the task on the status page 3 days ago, but it has since disappeared. Is this expected?
Sorry for the delay. It's been lost, probably due to the model having a problem that was too big for a normal log entry, and I don't remember. We'll discuss this and hopefully report back soon.
@RichardErkhov i force-queued it, BUT, it has worker rich1 set. But rich1 cannot convert this 3TB model, so please discuss first :)
Sorry for the delay. It's been lost, probably due to the model having a problem that was too big for a normal log entry, and I don't remember. We'll discuss this and hopefully report back soon.
thank you, no rush <3