Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
superduper
AI repositoriesSuperduper: End-to-end framework for building custom AI applications and agents.
git clone https://github.com/superduper-io/superduper.git -
KLM-1.5
Modelstext generation model by MinimaLabs · transformers
MinimaLabs/KLM-1.5 -
lumi-4b
Modelstext generation model by ceia-research
ceia-research/lumi-4b -
litgpt
AI repositories20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
git clone https://github.com/Lightning-AI/litgpt.git -
lumi-4b
Modelstext generation model by ceia-br
ceia-br/lumi-4b -
hands-on-llm
Agents & frameworks动手学大模型全栈:CS336 中文精讲 · PyTorch 手搓 Transformer · 单卡复现 Pretrain/SFT/LoRA/DPO/GRPO/RLVR · PEFT/Agent/RAG 落地(含真实实验、曲线与复现脚本)
git clone https://github.com/FRS2003/hands-on-llm.git -
GameScaling
Modelsimage text to text model by THUSI-Lab · transformers
THUSI-Lab/GameScaling -
keras-hub
AI repositoriesPretrained model hub for Keras 3.
git clone https://github.com/keras-team/keras-hub.git -
modern-llm-notebook
Docs & tutorialsA hands-on course on modern LLM architectures, training, and inference, with step-by-step PyTorch implementations and runnable notebooks.
git clone https://github.com/walkinglabs/modern-llm-notebook.git -
LoongForge
AI repositoriesA high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T-N1.7, FastWAM, Cosmos3, DreamZero, DeepSeek-V4, GLM-5.3, Kimi-K3 and more.
git clone https://github.com/baidu-baige/LoongForge.git -
nixtla
AI repositoriesTimeGPT-2.1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
git clone https://github.com/Nixtla/nixtla.git -
Meta: Llama 3.3 70B Instruct
ModelsThe Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
meta-llama/llama-3.3-70b-instruct -
Meta: Llama Guard 4 12B
ModelsLlama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
meta-llama/llama-guard-4-12b -
MoonshotAI: Kimi K2.5
ModelsKimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
moonshotai/kimi-k2.5
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.