This project aims to replicate mainstream open-source model architectures with limited computational resources, implementing mini models with 100-200M parameters.
☆298Aug 24, 2026Updated 2 months ago
Alternatives and similar repositories for Mini-LLM
Users that are interested in Mini-LLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 从零开始学大模型Transformer、GPT2、BERT pre-training and fine-tuning from scratch☆41Jul 1, 2024Updated 2 years ago
- 🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.☆4,872Oct 23, 2026Updated 2 weeks ago
- 手写 Triton kernel 实现的 Qwen3.5-0.8B 纯文本推理引 擎（batch=1, BF16, greedy）☆12Sep 10, 2026Updated last month
- ☆16Sep 16, 2025Updated last year
- Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning (Poster of A…☆14Dec 1, 2025Updated 11 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.
- An LLM training framework built from the ground up, featuring a custom BumbleBee architecture and end-to-end support for multiple open-so…☆72Aug 24, 2026Updated 2 months ago
- 👀 Train a 65M-parameter VLM from scratch in just 2h!☆8,822Oct 27, 2026Updated last week
- Reusable Codex/Claude skills and local agent configs☆30Oct 18, 2026Updated 2 weeks ago
- 从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)☆559Mar 23, 2025Updated last year
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,533May 17, 2026Updated 5 months ago
- ☆15May 10, 2026Updated 5 months ago
- A distributed training framework based on torchtitan☆111Aug 17, 2026Updated 2 months ago
- 手撕transformer并完成一个简单的机器翻译。☆23Feb 19, 2025Updated last year
- Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.☆1,286Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 一份面向实践者的 verl 框架使用教程。verl 是字节跳动开源的大语言模型强化学习训练框架，支持 PPO、GRPO 等多种算法，以及分布式训练、AgentRL 等场景。☆157Jul 2, 2026Updated 4 months ago
- 从零构建大模型：从预训练到RLHF的完整实践☆2,702Aug 21, 2026Updated 2 months ago
- slime is an LLM training framework for RL Scaling.☆8,806Updated this week
- 复现大模型相关算法及一些学习记录☆3,565Jul 2, 2026Updated 4 months ago
- Advanced LLM fine-tuning techniques: SFT (LoRA, QLoRA, DoRA, P-/Prefix-Tuning), GRPO, DPO, ORPO, KTO & PPO; composable correctness/format…☆14Updated this week
- GEMV implementation with CUTLASS☆21Aug 21, 2025Updated last year
- Implementation of ICCV 2025 paper "Growing a Twig to Accelerate Large Vision-Language Models".☆31May 23, 2026Updated 5 months ago
- AI-powered academic paper discovery and analysis agent☆27Aug 4, 2026Updated 3 months ago
- Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation☆1,101Aug 29, 2026Updated 2 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- CAD - Memory Efficient Convolutional Adapter for Segment Anything☆12Oct 4, 2024Updated 2 years ago
- My learning notes for ML SYS.☆7,653Oct 21, 2026Updated 2 weeks ago
- 🎓从0开始训练一个大模型Minimind项目的超详细解析，包括但不限于用到的架构，算法，以及大模型面试经验☆1,841May 25, 2026Updated 5 months ago
- [CVPR 2026 Highlight] Official implementation of Log-linear Sparse Attention (LLSA).☆94May 1, 2026Updated 6 months ago
- ☆21Apr 21, 2026Updated 6 months ago
- Building DeepSeek R1 from Scratch☆805Mar 21, 2025Updated last year
- My implementation of Stanford CS336 assignments.☆242Mar 15, 2026Updated 7 months ago
- dataset repository for an evaluation task☆10Jul 17, 2025Updated last year
- 面向订单查询、商品咨询、优惠比价、投诉处理等电商客服高频场景，构建端到端智能客服 Agent。支持多轮对话、工具调用、知识检索、记忆管理与自动化评估。☆26Updated this week
- 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.
- A from-scratch Prefill/Decode disaggregation inference engine for LLMs☆162May 10, 2026Updated 5 months ago
- 这是一个从头训练大语言模型的项目，包括预训练、微调和直接偏好优化，模型拥有1B参数，支持中英文。☆879Feb 18, 2025Updated last year
- 从零实现一个小参数量中文大语言模型。☆1,096Aug 22, 2024Updated 2 years ago
- ☆55Nov 22, 2025Updated 11 months ago
- Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning☆1,716Updated this week
- This is the public repository of AAAI 2024 paper "Is a Large Language Model a Good Annotator for Event Extraction"☆10Feb 16, 2024Updated 2 years ago
- learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen☆5,686Updated this week