Language Models

MiniMind is an educational training ground that rebuilds every stage of a modern language model—from tokenizer to RLHF—in raw PyTorch so you can see the gears turning instead of just calling high-level APIs.

A research framework that assigns LLMs to trading-floor roles—analyst, researcher, trader, risk manager—to debate and execute simulated stock decisions.

SGLang exists to push low-latency, high-throughput inference for LLMs and multimodal models from a single GPU up to massive clusters.

It turns your document pile into a persistent, interlinked wiki so the LLM doesn't have to re-read everything every time you ask a question.

WeKnora exists to turn scattered enterprise documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining wiki.

It exists to run large language models on virtually any hardware—from Apple Silicon to RISC-V to your browser—with zero external dependencies and minimal setup.

It automates the removal of transformer safety alignment so you don't have to hand-tune abliteration parameters or pay for expensive post-training.

A Python framework for building production multi-agent systems that leans on LLM reasoning instead of rigid prompt choreography.

It exists so you can download, run, and chat with open-weight LLMs locally through one CLI and REST API, keeping inference on your own silicon.

A hosted proxy that offers free, rate-limited API access to GPT, DeepSeek, and others for Chinese users who'd rather not tunnel through a VPN.

Because swapping from GPT-4o to Claude shouldn't require rewriting your request plumbing.

To give developers a single, general-purpose speech model that handles transcription, translation, and language identification by treating tasks as tokens to predict.

AirLLM slices giant transformers into layer shards so they fit in consumer VRAM without quantization or distillation.

It teaches how LLMs work by implementing tokenization, attention, pretraining, and finetuning in pure PyTorch, one notebook at a time.

It centralizes model definitions so the same architecture works across PyTorch, JAX, vLLM, and llama.cpp without rewrites.

Meetily transcribes and summarizes meetings entirely on-device, because "we don't log your calls" is a promise best kept by physics.

Curated tutorials and tool reviews covering vibe coding, DeepSeek, Cursor, and the rest of the generative-AI menagerie, maintained as a free, open-source knowledge base.

To teach developers agent engineering from scratch using smolagents, LangGraph, and LlamaIndex, capped by an automated benchmark.

Kronos recasts noisy, multi-dimensional candlestick data as hierarchical discrete tokens so an autoregressive Transformer can forecast financial markets like a language model.

A systematic Chinese tutorial for developers who want to stop treating LLMs as black boxes and hand-build a 215-million-parameter model from the ground up.