AI Infra2023
Provides a PyTorch-native platform for experimenting with and scaling generative AI training, including composable parallelism, checkpointing, float8, logging, and Llama recipes.
AI Audio2024
Clones a voice from a 5-second sample for zero-shot TTS, or fine-tunes on ~1 minute of audio for few-shot synthesis. Covers Chinese, English, Japanese, Korean, and Cantonese, with a WebUI bundling vocal separation, ASR, and dataset labeling.
Chatbot2024
Creates personalized digital avatars (AI twins) by fine-tuning LLMs on users' chat history and binding them to chatbots. Provides an end-to-end pipeline — chat export, preprocessing with privacy filters, SFT/LoRA training, and deployment (Telegram/Discord/Slack). Best with larger models and substantial chat data.
AI Train2024
Runs GPT-4o-class vision, speech, and full-duplex audio-video conversation on a 9B model small enough to deploy on phones and tablets. The 4.5 release scores 77.6 on OpenCompass and adds real-time bilingual voice with voice cloning.
AI Video2024
Generates short videos from text, images, or videos and ships a full training/inference pipeline with checkpoints and demos. Key features include multi-stage training (VAE / 3D-VAE), rectified-flow training, video compression modules, and support for 2s–16s clips at up to 720p. Best for researchers and engineers who can provide substantial GPU resources.
AI Train2024
End-to-end framework for running and reproducing foundation-model research workflows — from data curation and tokenization to training and evaluation. Emphasizes reproducibility by recording every step (including failed runs) and expressing experiments as dependency-ordered steps.
AI Train2024
Accelerates video generation with a unified framework for inference, finetuning, LoRA, distillation, sparse attention, and distributed execution for research and demos.
AI Train2024
Pretrained foundation model for zero-shot point and quantile forecasting on unseen time series, no per-dataset training. Decoder-only, trained on 100B real-world time-points; v2.5 (200M params) handles up to 16k context and 1k-step horizons.
AI Train2024
Streamlines the full lifecycle of foundation models — data prep, fine-tuning (SFT/LoRA/QLoRA/GRPO), evaluation, and deployment — with ready-to-run recipes, multi-engine inference support, and cloud/CLI workflows for both laptop experiments and large-scale runs.
AI Train2024
A community speedrun to train a 124M GPT as fast as possible on 8 H100s, all chasing a fixed 3.28 FineWeb loss. Successive records cut the run from llm.c's 45 minutes to under 1.4, mostly via the new Muon optimizer rather than more hardware.
AI Train2024
Trains a sub-100M-parameter LLM from scratch — pretraining, SFT, LoRA, DPO/RLHF, and distillation, sized from ~26M up to ~100M-plus dense and MoE. Headline figure: the ~64M minimind-3 variant's SFT stage runs 1 epoch in ~2h and ~3 RMB on one NVIDIA 3090.