deepspeedai / deepspeedai/DeepSpeedExamples
The model size does not change
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 6.8k
- Forks
- 1.1k
- Avg merge
- 2d 16h
- Merged PRs (30d)
- 1
Description
When I follow this https://www.deepspeed.ai/tutorials/model-compression/#2-tutorial-for-zeroquant-efficient-and-affordable-post-training-quantization run the zero_quant.sh or (quant_activation.sh and quant_weight.sh), the model size still is 418mb as the bert-base.
the clean_model weight still save as float32? Can u help me ? Thanks.
Contributor guide
No contributing guide indexed for this repository
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 linked ZeroQuant tutorial and inspect zero_quant.sh, quant_activation.sh, and quant_weight.sh, then trace how clean_model is saved. Compare the saved weights' dtype and file size with the bert-base output shown in the issue. Done means identifying why the quantized model remains 418 MB and confirming the corrected saved model size.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100