Search

An Open Source implementation of Notebook LM with more flexibility and features

Ongoing research training transformer models at scale

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

Contrastive Language Models (CLMs) are a new class of System One model trained with a contrastive learning objective that connects states and actions.

LiteRT and LiteRT-LM sample apps, model recipes, agent skills and utilities.

LLMs and VLMs with MLX Swift

自用Clash 策略组及规则 及Subconverter 相关资源备份

A framework for few-shot evaluation of language models.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

大模型基础: 一文了解大模型基础知识

AI terminal assistant for any OpenAI-compatible API. Features interactive chat TUI, command generation, code explanation, and streaming responses. Works with Ollama, OpenAI, LM Studio, and more.

LM Studio CLI

LM Studio localization

LM engine is a library for pretraining/finetuning LLMs

Keras based framework for neuro-symbolic LM systems

Run LLMs with MLX

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

A fully local and private Speech-To-Text app with cross-platform support, speaker diarization, Audio Notebook mode, LM Studio integration, and both longform and live transcription.

Train Large Language Models on MLX.

Library for text-to-text regression, applicable to any input string representation and allows pretraining and fine-tuning over multiple regression tasks.

面向中文输入法的语言模型：语料、n-gram 统计、字级神经模型，以及判断它们好坏的评测集

M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.

Hermes Agent made portable desktop for Windows — 100 tools, GUI, local models via LM Studio, TTS, Music, ComfyUI, workflows, tool maker. No install. No Docker. No admin rights.

Production focused Self-harnessed LM runtime (RLM) that allows the LM to call its sub-lm with DSPy signatures. Define your inputs, outputs, and tools — the model handles its own control flow. Get fully interpretable trajectories and performance that scales directly with model improvements. Without context rot.

[CVPR2026] TDMM-LM: Bridging Facial Understanding and Animation via Language Models