Random Sampling 支持
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.4k
- Forks
- 176
- PR merge metrics
- No merged PRs in 30d
Description
请问现在的模型支持做random sampling吗？我看现在src/cpm_live/generation/bee.py里面只写了beamsearch
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 by reading src/cpm_live/generation/bee.py, especially the existing beam-search generation path. Determine how generation options and model outputs are represented before defining the scope for random sampling. Done should mean the model supports random sampling alongside beam search, with the expected behavior and validation covered by tests if the repository provides a generation test entry point.
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
- Mostly clear
- Newbie friendliness
- 35/100