A full attention mechanism and transformer in pure go.

Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

AI Agent Builder in Python

This is a Python package to add tool calling capabilities to newly released LLMs on LangChain's ChatOpenAI library ahead of time before LangChain and LangGraph supports it!

LLM-as-SERP

MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset

the official code for "ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases"

The source code and dataset mentioned in the paper Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark.

Hammer: Robust Function-Calling for On-Device Language Models via Function Masking

Benchmark in Korean Context

Kanana: Compute-efficient Bilingual Language Models

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Stateful control of Large Language Models

DeepEP: an efficient expert-parallel communication library

FlashMLA: Efficient MLA decoding kernels

Scaling inference-time compute for LLM-as-a-judge, automated evaluations, guardrails, and reinforcement learning.

Flags SDK by Vercel

Making large AI models cheaper, faster and more accessible

LLM-powered multiagent persona simulation for imagination enhancement and business insights.

LLM Reasoning and Generation Benchmark. Evaluate LLMs in complex scenarios systematically.

Grok open release

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

The official Meta Llama 3 GitHub site

A simple screen parsing tool towards pure vision based GUI agent

Complex Function Calling Benchmark.