rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Models, Training & Serving
65 starred repositories in this area.
65 result(s)
deepseek-ai/DeepSeek-R1
DeepSeek 的開源推理模型,用大規模強化學習訓練出接近 o1 等級的思考能力。
unslothai/unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
hiyouga/LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
jingyaogong/minimind
🧠 Train a 64M-parameter LLM from scratch in just 2h!
google/langextract
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
stanfordnlp/dspy
DSPy: The framework for programming—not prompting—language models
alchaincyf/nuwa-skill
你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
QwenLM/Qwen3
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
huggingface/open-r1
Fully open reproduction of DeepSeek-R1
confident-ai/deepeval
The LLM Evaluation Framework
dair-ai/ML-YouTube-Courses
📺 Discover the latest machine learning / AI courses on YouTube.
ageron/handson-ml3
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
Lightning-AI/litgpt
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
dair-ai/AI-Papers-of-the-Week
🔥Highlighting the top ML papers every week.
ShishirPatil/gorilla
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
NVIDIA/personaplex
PersonaPlex code.
xorbitsai/inference
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
oumi-ai/oumi
Easily fine-tune, evaluate and deploy Qwen, Gemma, or any open weight LLM!
NVIDIA/garak
the LLM vulnerability scanner
NVIDIA/Isaac-GR00T
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
ai-dynamo/dynamo
A Datacenter Scale Distributed Inference Serving Framework
microsoft/TinyTroupe
LLM-powered multiagent persona simulation for imagination enhancement and business insights.
guardrails-ai/guardrails
Adding guardrails to large language models.
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training
jeinlee1991/chinese-llm-benchmark
非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。
shibing624/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
getzep/zep
Zep | Examples, Integrations, & More
openai/simple-evals
OpenAI 官方的輕量模型評測腳本,用來重現各家模型的標準 benchmark 分數。
PrimeIntellect-ai/verifiers
Our library for RL environments + evals
build-with-groq/g1
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains
predibase/lorax
Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs
ridgerchu/matmulfreellm
Implementation for MatMul-free LM.
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
WenjieDu/PyPOTS
A Python toolkit/library for reality-centric machine/deep learning & data mining on partially-observed time series, with 50+ SOTA neural network models for scientific analysis tasks (imputation, classification, clustering, forecasting, anomaly detection, cleaning) on incomplete industrial irregularly-sampled multivariate TS with NaN missing values
meta-llama/synthetic-data-kit
Tool for generating high quality Synthetic datasets
NVIDIA/RULER
This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?
AlibabaResearch/DAMO-ConvAI
DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.
Google-Health/medgemma
Google Health 的 MedGemma 醫療多模態開放模型,能讀醫學影像與病歷文字。
sail-sg/understand-r1-zero
Understanding R1-Zero-Like Training: A Critical Perspective
SakanaAI/self-adaptive-llms
A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!
cxcscmu/Craw4LLM
Official repository for "Craw4LLM: Efficient Web Crawling for LLM Pretraining"
Wang-ML-Lab/llm-continual-learning-survey
[CSUR 2025] Continual Learning of Large Language Models: A Comprehensive Survey
ZongqianLi/ReasonGraph
[ACL 2025 Demo] Repository for the demo and paper: ReasonGraph: Visualisation of Reasoning Paths
NVIDIA/Star-Attention
Efficient LLM Inference over Long Sequences
SamuelSchmidgall/AgentClinic
Agent benchmark for medical diagnosis
shangshang-wang/Tina
[ICLR 2026] Tina: Tiny Reasoning Models via LoRA
mtkresearch/MR-Models
聯發創新基地（MediaTek Research) 致力於研究基礎模型。我們將研究體現在適合繁體中文使用者的模型上，並在使用權許可的情況下，提供模型給學術界研究或產業界使用。
knowsuchagency/promptic
90% of what you need for LLM app development. Nothing you don't.
Jiaqi-Chen-00/ImBD
[AAAI 2025 oral] Official repository of Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
patrickloeber/llm-data-scrapers
A list of useful Open Source tools and scrapers to gather data for LLMs
CryptoAILab/JailbreakEval
[NDSS'25 Best Technical Poster] A collection of automated evaluators for assessing jailbreak attempts.
LibertFan/AI_Hospital
AI Hospital: Interactive Evaluation and Collaboration of LLMs as Intern Doctors for Clinical Diagnosis
FreedomIntelligence/Chain-of-Diagnosis
An interpretable large language model (LLM) for medical diagnosis.
ai-twinkle/Eval
High-performance LLM evaluation framework with parallel API calls — up to 17× faster than sequential tools. Supports box, math, and logit-based evaluation.
stream-bench/stream-bench
We propose a pioneering benchmark to evaluate LLM agents' ability to improve over time in streaming scenarios
LLMSELECTOR/LLMSELECTOR
替每個查詢挑選最合適模型的路由研究,兼顧成本與品質。
envy-ai/Wan2.1-quantized
Wan2.1, quantized and optimized so it fits on your 3090/4090
LiuYuWei/llm-colab-application
[ 演講用 ] LLM AI 模型 Colab 應用
AIAnytime/Qwen2-VL-Fine-Tuning
Qwen2 VL Fine Tuning using Llama Factory
Jakevin/o1-like-prompt
Reasoning chain prompt
DanielSun94/conversational_diagnosis
對話式醫療診斷的研究程式碼。
appier-research/streambench-final-project
The final project for Applied Deep Learning (ADL) 2024 @NTU lectured by Prof. Yun-Nung (Vivian) Chen. The project is based on the paper StreamBench: Towards Benchmarking Continuous Improvement of Language Agents.
TGoldsack1/BioLaySumm2024-evaluation_scripts
Evaluation script for the BioLaySumm 2024 shared task.
nullxjx/transformers-online-inference
使用 transformers 和 fastapi 搭建的LLM在线推理服务