丁立中的大模型算法工程作品集。聚焦 LLM / VLM 全链路的复现与优化，涵盖：① 预训练与微调（Pretrain / SFT / MoE / 多模态对齐）；② 强化学习对齐（PPO / GRPO / DAPO，含多奖励函数与 GAE）；③ 知识蒸馏（离线 KL 蒸馏、在线策略蒸馏、跨 Tokenizer 蒸馏、Embedding 蒸馏）；④ 前沿架构复现（DeepSeek MLA/MTP、Kimi Attention Residual、S1 Test-Time Scaling）；⑤ 工程应用（RAG、MCP 深度研究 Agent、PDF2Markdown、LLM 工具调用）。全部基于 PyTorch + Transformers 从零实现，支持 DeepSpeed 分布式训练与 B…
☆18May 26, 2026Updated 4 months ago
Alternatives and similar repositories for MYLLM
Users that are interested in MYLLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 9vms Global Cloud Servers: Starting at $49.95/month — Enterprise Dedicated Servers with Unlimited Traffic & High-Performance Bare Metal☆95Oct 7, 2026Updated 2 weeks ago
- python faceDetectionDNNMultiThread.py --prototxt deploy.prototxt.txt --model res10_300x300_ssd_iter_140000.caffemodel☆17Jul 29, 2019Updated 7 years ago
- Face segmentation,72 landmarks,attribute recoginition and face detection;人脸分割关键点识别,年龄预测,性别识别等☆13Aug 21, 2020Updated 6 years ago
- A ML-based tyre strategy engine based on real-time F1 data☆30Oct 17, 2026Updated last week
- TailNG UI is a signal-first Angular component library with Material-like components, framework-agnostic styling, and support for Angular …☆16Oct 9, 2026Updated 2 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- 一款可以浏览电脑文件的android app 目前只可以查看，下载 文件。内置ijkplayer，支持视屏播放（列表，小窗口，全屏），图片展示，滑动删除，断点下载。需要在局域网下使用，服务器也已上传（目前只有tomcat版）☆11Jul 12, 2018Updated 8 years ago
- vue，IM☆13Jun 8, 2018Updated 8 years ago
- An open-source non-official community implementation of the model from the paper: Surgical Robot Transformer (SRT): Imitation Learning fo…☆13Updated this week
- ☆12Apr 10, 2024Updated 2 years ago
- ☆14Sep 25, 2024Updated 2 years ago
- Metadata-first trust control plane for authorized security workflows, evidence retention, release trust, and business-flow proof.☆14Aug 11, 2026Updated 2 months ago
- Local hybrid RAG over a code knowledge graph. Indexes your codebase with tree-sitter + embeddings + a relationship graph and serves preci…☆15May 29, 2026Updated 4 months ago
- 吴恩达深度学习课程笔记PyTorch版☆21Nov 2, 2025Updated 11 months ago
- To appear in CVPR 2023 VISION workshop☆12Jun 25, 2023Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Design apps visually. AI builds them for you. Zero coding.... Created at https://coslynx.com☆13Oct 12, 2026Updated last week
- Parametric waveguide and horn designer with real-time 3D preview, built-in BEM simulation (Metal-accelerated), CAD round-trip, and measur…☆18Oct 18, 2026Updated last week
- Convenient and efficient open-source toolbox for near infrared spectra auto preprocessing☆12May 29, 2024Updated 2 years ago
- 2019秋哈工大机器学习实验+期末考试题☆12Nov 30, 2019Updated 6 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…☆20Aug 10, 2025Updated last year
- RTS game inspired by AOE. using herd algorithm and crowd dynamics, Genetic algorithms, Neural Network, Powered by Urho3D☆14Updated this week
- Local-first persistent memory for AI agents — captures conversations, extracts durable knowledge, resolves conflicts, and reuses relevant…☆18Sep 22, 2026Updated last month
- e2e encrypted secret sharing via p2p exchanges & embedded vaults☆12Oct 3, 2026Updated 3 weeks ago
- Deepseek-r1复现科普与资源汇总☆22Mar 5, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- share keet room invite via http link☆12Aug 21, 2026Updated 2 months ago
- A-share ETF动量轮动策略回测框架☆31Oct 15, 2026Updated last week
- Globally reasoned multi-task model for surgical scene understanding. A multi-task model for segmentation and scene graph. Offical Impleme…☆15May 5, 2022Updated 4 years ago
- Header-only C++20 audio DSP for real-time and offline processing. Filters, effects, analog circuit models, automatic dynamics, stereo too…☆19Oct 13, 2026Updated last week
- ☆17May 14, 2026Updated 5 months ago
- Edge service to generate embeddable dynamic 🖼️ OpenGraph image. Powered by @vercel/og☆17Sep 15, 2026Updated last month
- Self-hosted, agentic vulnerability research for binaries & firmware: an AI agent decompiles, fuzzes, and verifies exploits inside a sandb…☆21Aug 15, 2026Updated 2 months ago
- rentals at Dhaka ? we got you☆12Sep 20, 2026Updated last month
- Joint Embedding of Deep Visual and Semantic Features for Medical Image Report Generation☆19Nov 13, 2025Updated 11 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.
- This project comprises the datasets and Python versions of two codebase: (1) Semantic-SuPer: A Semantic-aware Surgical Perception Framewo…☆20Jun 17, 2025Updated last year
- AI coding harness: AST-powered code navigation, impact analysis, phased task chains, and cross-session memory.☆17Sep 5, 2026Updated last month
- Firmion is DSL and engine for firmware image generation.☆15Jul 7, 2026Updated 3 months ago
- Integrating Symbolic Programming and Neuromorphic Modeling for Edge Labs with NVIDIA Jetson, DGX Spark, and GPU-based DNN/ML Systems☆16Updated this week
- A thoughtful and versatile cross-platform script runner, playground, toolkit, test-bed, and proc_macro and terminal theming resource for …☆14Oct 7, 2026Updated 2 weeks ago
- Obsidian 图文导出插件：将 Markdown 笔记一键生成小红书 / RedNote、抖音图文、Bilibili 图文等社媒卡片，支持主题、封面和批量导出。☆29Jun 18, 2026Updated 4 months ago
- ☆24May 8, 2025Updated last year