[QA] Why is InternLM2-Chat-SFT based on InternLM2-Base instead of InternLM2? #606
Answered
by
ZwwWayne
underspirit
asked this question in
Q&A
-
Describe the question.InternLM2 is an enhanced model based on InternLM2-Base, and its capabilities should be better in many domain. Why isn't the subsequent SFT model based on it? |
Beta Was this translation helpful? Give feedback.
Answered by
ZwwWayne
Jan 17, 2024
Replies: 1 comment
-
This is simply due to the time issue. InternLM2 and InternLM2-Chat are trained parallelly due to limited time for release. Furthermore, InternLM2 and InternLM2-Chat are optimized for different capability dimensions as you can see from the evaluation results. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
ZwwWayne
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This is simply due to the time issue. InternLM2 and InternLM2-Chat are trained parallelly due to limited time for release. Furthermore, InternLM2 and InternLM2-Chat are optimized for different capability dimensions as you can see from the evaluation results.