deepspeedai / deepspeedai/DeepSpeed
[REQUEST] How to quantize and preshard the bloomz 176b model？
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 43.1k
- Forks
- 5k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 112
Description
The microsoft/bloom-deepspeed-inference-int8 model provides an excellent presharded quantization model. I would like to know if the code to generate such a model can be provided?
Also can the same presharded quantization model be provided for the Bloomz model?
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 does not name any files, tests, or entry points. Start by reviewing the existing microsoft/bloom-deepspeed-inference-int8 model and DeepSpeed's support for quantizing and presharding Bloomz 176b. Done would require identifying whether the generation process can be shared and whether a presharded Bloomz model can be provided.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 18/100