https://huggingface.co/Qwen/WorldPM-72B-HelpSteer2

#1291
by ConicCat - opened

https://huggingface.co/Qwen/WorldPM-72B-HelpSteer2
Qwen 2.5 72B with a continued pretrain (with dpo lol) and the mystical Apache 2.0 license instead of the clunky Qwen license.
Kinda interested to see if it's better than L3.3

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#WorldPM-72B-HelpSteer2-GGUF for quants to appear.

Unfortunately, the Qwen2ForRewardModel architecture is not supported by llama.cpp at this time

RIP, thanks for trying

ConicCat changed discussion status to closed

Sign up or log in to comment