You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
All of the keys of weight file begin with 'rwkv.' compared to convert.py.
The .att. in convert.py should be replaced with .attention..
The value of rwkv.blocks.0.attention.time_decay is a 1d tensor. The headsnume and headsize in convert.py can't unpacke from w[f"rwkv.blocks.0.attention.time_decay"].shape
I don't know how to fix the third problem.
The text was updated successfully, but these errors were encountered:
Hi @kip234 I am glad to tell you that the reason you cannot convert the v4 world model is due to the fact it has been deprecated in favor of the v5 world model (Also known as the Eagle models)!
You can find the checkpoints here: https://huggingface.co/BlinkDL/rwkv-5-world/tree/main
I have tried to convert the weight file which i download from https://huggingface.co/RWKV/rwkv-4-world-169m with
convert.py
. I found the following problems.convert.py
..att.
inconvert.py
should be replaced with.attention.
.rwkv.blocks.0.attention.time_decay
is a 1d tensor. Theheadsnume
andheadsize
inconvert.py
can't unpacke fromw[f"rwkv.blocks.0.attention.time_decay"].shape
I don't know how to fix the third problem.
The text was updated successfully, but these errors were encountered: