Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
- apple-silicon
- deep-learning
- huggingface
- large-language-models
142,273 visible repositories in the index
769–792 of 1,943 · Most stars
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
Korvus is a search SDK that unifies the entire RAG pipeline in a single database query. Built on top of Postgres with bindings for Python, JavaScript, Rust and C.
🌌 Give a soul to your favorite characters. Soul of Waifu is a desktop roleplay & AI companion app featuring Live2D/VRM avatars, voice chat & local LLM. Evolve together across immersive chat, RPG adventures, and your desktop.
tl/dw (Too Long, Didn't Watch): Your Personal Research Multi-Tool - a naive attempt at 'A Young Lady's Illustrated Primer' (Open Source NotebookLM)
Ragflow-Plus 是 Ragflow 的二次开发版本,使其更为简洁实用
Your entire engineering context, deeply understood
The repository host gives no description.
Pre-trained ELMo Representations for Many Languages
LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
Things you can do with the token embeddings of an LLM
BrowserGym, a Gym environment for web task automation
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
Simple web service providing a word embedding model
The repository host gives no description.
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
bloom - evaluate any behavior immediately 🌸🌱
Traditional Mandarin LLMs for Taiwan
Secrets of RLHF in Large Language Models Part I: PPO
An IDA plugin for binary file analysis, powered by AI models such as OpenAI and DeepSeek.
An alignment auditing agent capable of quickly exploring alignment hypothesis
Webchat to API
Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI