deepspeedai / deepspeedai/DeepSpeed
By DeepSpeed， How do I need to achieve: access my database and get the data statistics I want？
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 43.1k
- Forks
- 5k
- Avg merge
- 4d 15h
- Merged PRs (30d)
- 112
Description
First of all, thank you so much for sharing your project!
At present, I have a requirement, which is as follows:
First, I have a database, which records the relevant data of products produced by my own factory every day. Then I need to use DeepSpeed to train a model. This model allows me to access the model in a conversational manner, let the model tell me the data situation of the current database and present it to me in the statistical form I need.
Due to my current limited computing power, the GPU computing power I currently have is 2 Nvidia graphics cards with V100 32GB video memory.
Therefore, what kind of corpus and which specification pre-training model do I need to prepare to realize this function?
Looking forward to your reply, thank you very much！
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. It asks for guidance on connecting a database to a conversational model, preparing a corpus and choosing a pretrained model for two V100 GPUs; the requested outcome is a defined approach for providing database statistics through the model.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- databases, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 15/100