手撕transformer并完成一个简单的机器翻译。
☆22Feb 19, 2025Updated last year
Alternatives and similar repositories for transformer-from-scratch
Users that are interested in transformer-from-scratch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A modular framework for training and inference of (compressed) multi-vector retrieval across any modality.☆22Apr 4, 2026Updated 4 months ago
- 本项目从零开始构建并优化了一个千万参数级别的大规模预训练语言模型，涵盖预训练、有监督微调（SFT）和R1推理蒸馏三个阶段。项目采用自定义Transformer架构（包括RMSNorm、分组注意力、多Query机制、SwiGLU激活和RoPE位置编码），实现高效的长文本处理和…☆23Mar 10, 2025Updated last year
- Official PyTorch Implementation for CAiD: Context-Aware Instance Discrimination for Self-supervised Learning in Medical Imaging - MIDL 20…☆11Apr 15, 2022Updated 4 years ago
- Detect complete and incomplete circular shapes in noisy images☆18Apr 7, 2020Updated 6 years ago
- [AAAI 2023] Pytorch Implementation for AAAI2023 paper: One-for-All: Proposal Masked Cross-Class Anomaly Detection☆15Oct 31, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- FastTrack4LLM 是一个为大模型学习者准备的大模型学习与实践框架，帮助他们轻松掌握大模型的核心原理与训练流程，让每个人都能真正理解大模型的内部机制。本项目不仅完整复现了 LLaMA、Qwen、DeepSeek 等主流开源大模型架构，还覆盖了大模型的全生命周期：To…☆31Nov 6, 2025Updated 9 months ago
- ☆19Apr 23, 2026Updated 3 months ago
- 国科大课程评价静态站：支持搜索筛选、评分汇总、批量填写导出并通过问卷提交（隐私友好、无后端）。☆43Jan 5, 2026Updated 7 months ago
- Author's PyTorch implementation of paper Reinforced Imitative Trajectory Planning for Urban Automated Driving☆17Aug 7, 2025Updated last year
- [原理解析] 大模型基本功（手撕Transformer模型、手撕PPO、GRPO、DPO训练器）☆30Jul 8, 2025Updated last year
- 大三下Web课设 - 中南大学主页 - JavaWeb☆13Dec 6, 2019Updated 6 years ago
- 基于langchain1.0框架下的rag问答机器人☆17Nov 25, 2025Updated 8 months ago
- AI Wiki of XJTU☆26Jul 9, 2026Updated last month
- Implementation of TrajDiff: End-to-end Autonomous Driving without Perception Annotation☆18May 28, 2026Updated 2 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [ICLR 2024] Contrastive Learning Is Spectral Clustering On Similarity Graph (https://arxiv.org/abs/2303.15103)☆21Sep 17, 2024Updated last year
- ☆22May 26, 2024Updated 2 years ago
- ECCV2022-Paper-List☆19Aug 27, 2022Updated 3 years ago
- 基于 RAG 技术的智能问答系统，支持多知识库管理、混合检索（稠密 + 稀疏向量）、流式对话、检索质量评估。适用于金融政策法规、企业内部文档等场景。☆26May 27, 2026Updated 2 months ago
- Python sample codes for robotics algorithms.☆19Dec 18, 2022Updated 3 years ago
- 本项目基于 HuggingFace Transformers 和 PEFT (LoRA)，专注于中文法律文本的因果语言模型微调。首先，利用 Qwen2-70B 大模型对下载的法律裁判文书进行思维链（Chain-of-Thought, CoT）抽取，实现模型蒸馏与知识迁移；随…☆19Aug 10, 2025Updated last year
- learning based uncertainty-aware 3D offroad navigation☆32Sep 1, 2023Updated 2 years ago
- 大模型面试八股文☆48May 31, 2025Updated last year
- 1.基于qwen3大模型或领域化qwen3大模型 2.neo4j知识图谱 3.向量检索 4.文本检索 5.问答实现☆24Feb 4, 2026Updated 6 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences (IROS 2020)☆22May 16, 2022Updated 4 years ago
- ☆28Feb 21, 2026Updated 5 months ago
- Official repository for TimeDRL: Disentangled Representation Learning for Multivariate Time-Series, accepted at ICDE 2024.☆28Apr 7, 2024Updated 2 years ago
- [ICLR2026] The first W4A4KV4 quantized + 50% sparse LLMs!☆33Jan 26, 2026Updated 6 months ago
- Reimplementation of "Autoregressive Unsupervised Image Segmentation" by Ouali et al (ECCV 2020)☆24Oct 31, 2021Updated 4 years ago
- ☆30Apr 21, 2026Updated 3 months ago
- 一年过去了，你在洗脚食堂里花的钱都花在哪儿了？☆151Dec 27, 2024Updated last year
- 记录RAG学习过程中的相关知识和方法☆33Sep 23, 2025Updated 10 months ago
- 大模型训练、推理、推荐系统相关☆30Nov 30, 2025Updated 8 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆35Jun 12, 2026Updated last month
- ☆25Mar 15, 2023Updated 3 years ago
- langchain-study☆31Jul 21, 2026Updated 2 weeks ago
- 超简单使用监督微调SFT和强化学习RL去训练领域Agent☆34Oct 20, 2025Updated 9 months ago
- This project aims to replicate mainstream open-source model architectures with limited computational resources, implementing mini models …☆291Aug 4, 2026Updated last week
- ☆60Mar 22, 2024Updated 2 years ago
- MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence☆62Mar 11, 2026Updated 5 months ago