beam
beam
Discover
PulseActivityAnalyticsBest forMapOrgs
Niches
AgentsMCPRAGCoding AssistantsInference & ServingVector DBs
Personal
WatchlistCompareWeekly report
?
Sign in
magic link · no password
LIVE──────── · ──:──:── UTCabout
beam
beam
Discover
PulseActivityAnalyticsBest forMapOrgs
Niches
AgentsMCPRAGCoding AssistantsInference & ServingVector DBs
Personal
WatchlistCompareWeekly report
?
Sign in
magic link · no password
Back to Pulse
Tool profile

Enping-Hu/minimind-deep-dive

stable
Single maintainer

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。

deep-learningdpofine-tuningfrom-scratchgrpolarge-language-modelsllmllm-training
Velocity score
0.03/ 10
[STARS]
193
[FORKS]
11
[CONTRIBUTORS]
1
[LAST_COMMIT]
19d ago
OPEN_ON_GITHUB
Velocity class: stable
Is Enping-Hu/minimind-deep-dive still actively maintained?
[VR]

This tool is in the Velocity Report when it moves. Get the weekly numbers.

Score breakdown
544/ 1000
fine-tuning · Enping-Hu/minimind-deep-dive
Velocity50%
Adoption30%
Maintenance15%
Community5%
[CODE_GROWTH]
645
[INSTALL_VEL]
500
[ACTIVITY]
421
[COMMUNITY_SIGNAL]
176

Terminal score: 0–1000 raw, weighted across 4 dimensions. Public score: 0–10 normalized (shown in the 30-day stars chart above).

LIVE──────── · ──:──:── UTCabout