deepseek-ai / deepseek-ai/DeepSeek-Math

Model Size Choices in Evaluation

Open
#39 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
3.4k
Forks
592
PR merge metrics
No merged PRs in 30d

Description

For evaluation, the choices of model size are fixed to be ['1b', '7b', '13b', '33b', '34b', '70b'].

/evaluation/run_subset_parallel.py:

`parser.add_argument("--model-size", type=str, choices=['1b', '7b', '13b', '33b', '34b', '70b'], default="7b")`

(1) Why fix the choices?
(2) As I want to evaluate 3B model, can I just add '3b' in the list? Will this cause any problem?

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.