Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
- interpretability
- mechanistic-interpretability
- qwen
- steering
132,241 visible repositories in the index
97–120 of 255 · Most stars
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
Aila(AI超元域): The premier AI integration tool for Windows, macOS, and Android. Ask once, get answers from 10+ AIs like ChatGPT, Gemini, Claude3, Copilot, Poe, perplexity and more. Features customizable AI and prompts.
CORTEX RAG is an enterprise retrieval and knowledge assistant that helps teams find accurate answers from company data with citations, permission-aware retrieval, and fast deployment
Implementing DeepSeek R1's GRPO algorithm from scratch
An unofficial C#/.NET SDK for accessing the OpenAI GPT-3 API
Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.
An optimized quantization and inference library for running LLMs locally on modern consumer-class GPUs
Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
Developer APIs to Accelerate LLM Projects
Unified Communication X (mailing list - https://elist.ornl.gov/mailman/listinfo/ucx-group)
A very simple GRPO implement for reproducing r1-like LLM thinking.
All-in-One Multimodal Parsing Engine + Ontology-Powered, LLM Wiki-Driven AI-Ready Knowledge Engine
🦎 A lightweight, streaming-native, multi-protocol gateway for AI, APIs, and real-time data. Route LLM requests across providers, govern MCP tools, and connect Kafka, MQTT, and HTTP through one high-performance engine with shared security and observability.
An AI search engine inspired by Perplexity
An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation
An enterprise AI workspace for model routing, multimodal chat, files, tools, billing, identity, and operations.
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
Stanford NLP Python library for Representation Finetuning (ReFT)
Chat language model that can use tools and interpret the results
Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.
🤖 Deploy a private ChatGPT alternative hosted within your VPC. 🔮 Connect it to your organization's knowledge base and use it as a corporate oracle. Supports open-source LLMs like Llama 2, Falcon, and GPT4All.
Multimodal RL training framework for diffusion & omni models