From 1ea113ea2c4a9fa521af82348feb9ebccc2d6898 Mon Sep 17 00:00:00 2001 From: jingyaogong Date: Sun, 19 Apr 2026 14:51:47 +0800 Subject: [PATCH] [update] readme --- README.md | 12 ++++-------- README_en.md | 12 ++++-------- 2 files changed, 8 insertions(+), 16 deletions(-) diff --git a/README.md b/README.md index 5615082..2722d9f 100644 --- a/README.md +++ b/README.md @@ -39,7 +39,7 @@ * 这不仅是一个大语言模型全阶段开源复现项目，也是一套面向 LLM 入门与实践的教程。 * 希望此项目能为更多人提供一个可复现、可理解、可扩展的起点，一起感受创造的乐趣，并推动更广泛 AI 社区的进步。 -> 注：本项目基于 Apache 2.0 协议开源，完全免费；“2小时” 基于 NVIDIA 3090 硬件设备（单卡）预估，“3块钱” 指 GPU 服务器租用成本，具体规格详情见下文。 +> 注：本项目基于 Apache 2.0 协议开源，完全免费。“2 小时” 指 SFT 阶段在单张 NVIDIA 3090 上跑完 `1 epoch` 的实测耗时，“3 块钱” 指对应时段的 GPU 租用成本。 --- @@ -167,9 +167,10 @@ minimind2系列旧模型均经过权重映射+（微调训练）QKVO线性层校 -
- 2025-02-09 +
+ More... +**2025-02-09** - 迎来发布以来重大更新，Release minimind2 Series。 - 代码几乎全部重构，使用更简洁明了的统一结构。 如有旧代码的兼容性需要，可访问[🔗旧仓库内容🔗](https://github.com/jingyaogong/minimind/tree/6e9cd28ef9b34a0a10afbdf6f59e65cb6e628efb)。 @@ -183,11 +184,6 @@ minimind2系列旧模型均经过权重映射+（微调训练）QKVO线性层校 - minimind2具备一定的英文能力！ - 更新minimind2与第三方模型的基于更多大模型榜单测试性能的结果。 -
- -
- More... - **2024-10-05** - 为MiniMind拓展了多模态能力之---视觉 - 移步孪生项目[minimind-v](https://github.com/jingyaogong/minimind-v)查看详情！ diff --git a/README_en.md b/README_en.md index 079851f..038c2d2 100644 --- a/README_en.md +++ b/README_en.md @@ -39,7 +39,7 @@ * This is not only a full-stage open-source reproduction project for large language models, but also a tutorial oriented towards LLM introduction and practice. * We hope this project can provide a reproducible, understandable, and extensible starting point for more people, to share the joy of creation together and promote the progress of the broader AI community. -> Note: This project is open-sourced under the Apache 2.0 license and is completely free; "2 hours" is estimated based on NVIDIA 3090 hardware (single GPU), and "3 CNY" refers to GPU server rental cost. See below for detailed specifications. +> Note: This project is open-sourced under the Apache 2.0 license and is completely free. "2 hours" refers to the measured time to run `1 epoch` of the SFT stage on a single NVIDIA 3090, and "3 CNY" refers to the corresponding GPU rental cost for that duration. --- @@ -166,9 +166,10 @@ After this update, maintenance for the entire `minimind-v1` series will be disco
-
- 2025-02-09 +
+ More... +**2025-02-09** - Major update since release, Release minimind2 Series. - Code almost entirely refactored, using a more concise and clear unified structure. For compatibility needs with old code, visit [🔗Old Repository Content🔗](https://github.com/jingyaogong/minimind/tree/6e9cd28ef9b34a0a10afbdf6f59e65cb6e628efb). @@ -182,11 +183,6 @@ After this update, maintenance for the entire `minimind-v1` series will be disco - minimind2 has certain English language capability! - Updated benchmark test performance results of minimind2 vs third-party models on more LLM leaderboards. -
- -
- More... - **2024-10-05** - Extended multimodal capability for MiniMind --- Vision - Visit the sibling project [minimind-v](https://github.com/jingyaogong/minimind-v) for details!