deepseek-ai / deepseek-ai/DeepSpec
Release speculators used for ablations
Open
- Dominant language
- Python
- Stars
- 7.1k
- Forks
- 667
- PR merge metrics
- No merged PRs in 30d
Description
Is it possible to release the speculators trained for different block sizes (Figure 4) for more rigorous benchmarking by researchers?
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by locating the training and evaluation entry points and the configurations used for the different block sizes in Figure 4. Confirm which trained speculator artifacts can be published, how researchers would retrieve and benchmark them, and consider the work done when those artifacts and usage details are released.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, release
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100