Error when converting NMT model with ALiBi or RoPe
Open
Nobody has claimed this yet.
enhancement
question
- Dominant language
- C++
- Stars
- 4.7k
- Forks
- 536
- Avg merge
- 12h 12m
- Merged PRs (30d)
- 4
Description
Hello, thank you for a great project!
I am getting this error when using ALiBi or RoPe positional encoding in a tranformer NMT model from OpenNMT-py:
KeyError: 'encoder.embeddings.make_embedding.pe.pe'
Absolute and relative positional encodings are working with the converter script.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the converter script and reproduce conversion of an OpenNMT-py Transformer NMT model using ALiBi or RoPe positional encoding. Compare this path with the working absolute and relative positional encodings, and trace the reported KeyError for encoder.embeddings.make_embedding.pe.pe. Done means the affected models convert without that error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp, python
- Domain
- machine-learning, tooling
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100