[GH-ISSUE #14] Support for DeepSeek-R1 Fine tuning #10

Open
opened 2026-10-26 21:06:41 +00:00 by bsakaguchi · 0 comments
Owner

Originally created by @goswamig on GitHub (Jan 28, 2025).
Original GitHub issue: https://github.com/deepseek-ai/ESFT/issues/14

Given the DeepSeek MoE architecture is backbone for DeepSeek-R1 and DeepSeek-V3, can this package be extended to support train/fine tuning for DeepSeek-R1/v3 ?

Originally created by @goswamig on GitHub (Jan 28, 2025). Original GitHub issue: https://github.com/deepseek-ai/ESFT/issues/14 Given the DeepSeek MoE architecture is backbone for DeepSeek-R1 and DeepSeek-V3, can this package be extended to support train/fine tuning for DeepSeek-R1/v3 ?
Sign in to join this conversation.
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
deepseek-ai/ESFT#10
No description provided.