https://huggingface.co/BeaverAI/Qwen2.5-QwQ-RP-Draft-v0.2-1.5B
#794
by
Laetilia
- opened
I've found new version (v0.2) of specialized model for QwQ RP draft - (at least in theory) being plugged into speculative decoding, it'll allow for full-sized QwQ to go faster (in Role Play). I recently found wonderful QwQ RP fine-tune named Snowdrop-v0 (which you already quantized!), and I think that this mini-model would be a nice addition to speed it up! Please, if that's alright, make GGUFs out of this Qwen2.5-QwQ-RP-Draft-v0.2-1.5B ^_^
Sure, 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#Qwen2.5-QwQ-RP-Draft-v0.2-1.5B-GGUF for quants to appear.
mradermacher
changed discussion status to
closed