nagayama0706

/

model_merge

like 0

Hi Chiyuri,
Thank you for sharing your merged models!
I was wondering if you have encountered the following error since Flan-T5-base is an encoder-decoder model and how you solved it:

CopyTraceback (most recent call last):
  File "/usr/local/bin/mergekit-yaml", line 8, in <module>
    sys.exit(main())
  File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1157, in __call__
    return self.main(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1078, in main
    rv = self.invoke(ctx)
  File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1434, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 783, in invoke
    return __callback(*args, **kwargs)
  File "/content/mergekit/mergekit/options.py", line 82, in wrapper
    f(*args, **kwargs)
  File "/content/mergekit/mergekit/scripts/run_yaml.py", line 47, in main
    run_merge(
  File "/content/mergekit/mergekit/merge.py", line 46, in run_merge
    model_arch_info = [
  File "/content/mergekit/mergekit/merge.py", line 47, in <listcomp>
    get_architecture_info(m.config(trust_remote_code=options.trust_remote_code))
  File "/content/mergekit/mergekit/architecture.py", line 366, in get_architecture_info
    raise RuntimeError(f"Unsupported architecture {arch_name}")
RuntimeError: Unsupported architecture T5ForConditionalGeneration

When I use your scripts on the LazyMergekit, I have been stuck on the error above.
Thank you so much, and I'm looking forward to hearing from you!