Qwen2 initialization
#1
by
grib0ed0v
- opened
Guys, first of all, kudos to you!!
And thanks for sharing such cool model with community🎉
Could you clarify if you used pretrained Qwen2 checkpoint ?
And if yes, which one, just interested if you experiment with Base, Instruct, Math-Instruct, Coder-Instruct models and noticed some difference?
Hi, thanks
Base model: Qwen/Qwen2.5-1.5B-Instruct
grib0ed0v
changed discussion status to
closed