DeepSeek-671B-SFT-Guide

An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案,包含从训练到推理的完整代码和脚本,以及实践中积累一些经验和结论。)

ScienceOne-AI/DeepSeek-671B-SFT-Guide

View on GitHub ↗

An open-source solution for full parameter fine-tuning of DeepSeek-V3/R1 671B, including complete code and scripts from training to inference, as well as some practical experiences and conclusions. (DeepSeek-V3/R1 满血版 671B 全参数微调的开源解决方案,包含从训练到推理的完整代码和脚本,以及实践中积累一些经验和结论。)

DeepSeek-671B-SFT-Guide grew -0.5% in the last 30 days, ranks 21st of 103 in Pretraining & Training, last commit 592 days ago.

Star trajectory

80 days tracked
2026-08-07811 stars today2026-10-26
Momentum

-0.5% in 30d, below the Pretraining & Training median of +0.0%.

Maintenance

Last commit 592 days ago, staler than the median of 164d.

How it compares in Pretraining & Training

DeepSeek-671B-SFT-Guide
811
stars
-0.5% 30d
commit 592 days ago
Pretraining & Training median
316
stars
+0.0% 30d
commit ~164d ago
Leader · maxtext
2.5k
stars
+0.9% 30d
commit today

Ranked 21st of 103 by stars.

Language
Python
License
Apache License 2.0
Contributors
2
Forks
97
Watchers
8
Open issues
1
Releases
0
Created
2025-03-07
Stars this week
-1

You've seen where DeepSeek-671B-SFT-Guide stands today.

Get the moves before everyone else: the 5 Pretraining & Training repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain DeepSeek-671B-SFT-Guide?

Claim this page to add your own call-to-action.

Claim this page