-
KRAFTON Inc.
- Seoul, Republic of Korea
Stars
Janus-Series: Unified Multimodal Understanding and Generation Models
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
[NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling better-reasoned decision-making for daily task planning problems.
An Open Large Reasoning Model for Real-World Solutions
How to create rational LLM-based agents? Using game-theoretic workflows!
Papers and resources related to the security and privacy of LLMs 🤖
[ICLR 2025] Automated Design of Agentic Systems
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"
Run PyTorch LLMs locally on servers, desktop and mobile
Official implementation of Half-Quadratic Quantization (HQQ)
Code Repository of Evaluating Quantized Large Language Models
Composable building blocks to build Llama Apps
Agentic components of the Llama Stack APIs
Finetuning Large Language Models on One Consumer GPU in 2 Bits
A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…
General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for…
OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
ReFT: Representation Finetuning for Language Models
NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference
Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI
Finetune Llama 3.3, Mistral, Phi-4, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248