Convert model.bin (fp32) to model.bin (int8)
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 4.7k
- Forks
- 536
- Avg merge
- 12h 12m
- Merged PRs (30d)
- 4
Description
I have a pretrained model.bin file which was earlier converted using OpenNMTPy converter using fp32 quantisation. Now i want to reduce the size of the model and thought of quantising it to int8. But, I was only able to find ways to quantise it upon loading of the model, not able to find how to save it for further use.
Any idea how it can be achieved?
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
The issue mentions a model.bin file, the OpenNMTPy converter, and quantization during model loading, but names no repository files or tests. Start by locating the loading-time quantization and model serialization entry points, then determine whether an int8 model can be saved for later use. Done should include a documented, repeatable conversion path and coverage for loading the saved model.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100