Markr.AI's repositories
Korean-SAT-LLM-Leaderboard
Korean SAT leader board
COT_steering
This repository aims to develop CoT Steering based on CoT without Prompting. It focuses on enhancing the model’s latent reasoning capability without additional training by leveraging Test-Time Scaling techniques.
KO-Platypus
[KO-Platy🥮] Korean-Open-platypus를 활용하여 llama-2-ko를 fine-tuning한 KO-platypus model
AutoRAG-tutorial-ko
AutoRAG 한국어 튜토리얼을 위한 레포입니다.
AutoRAG-example-korean-embedding-benchmark
AutoRAG example about benchmarking Korean embeddings.
KoLLM_Eval
한국어 벤치마크 평가 코드 통합본(?)
Korean-OpenOrca
OpenOrca-KO dataset을 활용하여 llama2를 fine-tuning한 Korean-OpenOrca
OpenFlaminKO
Polyglot을 활용한 image-text multimodal
CoT-llama2
Chain-of-thought 방식을 활용하여 llama2를 fine-tuning
AutoRAG-tutorial
Super simple tutorial for AutoRAG beginners
ecommerce-multi-agent
Multi-agent inbound voice customer support system for e-commerce using LiveKit & Twilio
RAGchain-docs
Documentation for RAGchain (no longer maintain)
Ovis2-FFT-Korean
Korean Large MultiModal FFT Code
AutoRAG-example-tokenizer-benchmark
Benchmark with AutoRAG. Korean bm25 tokenizer benchmark.
multi-survey-agent
Telephony agent to automate phone multi-question and conditional surveys with LiveKit, Twilio, and OpenAI real-time APIs
KO-VLM-Benchmark
AIHUB 시각화자료질의응답 데이터셋을 기반으로 만든 VLM 벤치마크 데이터셋
m2b-code-interpreter
Running E2B-style Sandbox on Modal
AutoRAG-template
Template for new AutoRAG project
Logickor-Gemma2-Eval
Logickor self-evaluation code (with gemma2)
phone-survey-agent
Telphony agent for automating phone surveys using LiveKit, Twilio, and OpenAI Realtime API
senior-care-agent
Senior Care Agent Recipe using LiveKit & Twilio
KHU-policy-RAG-demo
KHU RAG demo optimized by AutoRAG
recipe-RAG-demo
recipe RAG demo optimized by AutoRAG