- Seoul, Republic of Korea
-
21:54
(UTC +09:00) - https://l-yohai.github.io/portfolio/
- in/l-yohai
Highlights
Block or Report
Block or report l-yohai
Contact GitHub support about this userβs behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
Code and example data for the paper: Rule Based Rewards for Language Model Safety
This hands-on lab aims to alleviate some of that headache by demonstrating how to create/augment a QnA dataset from complex unstructured data, assuming a real-world scenario. The sample aims to be β¦
Open source and AI-powered web search engine: local, private, dockerized and supported by a fluffy llamaπ¦
Minimalistic large language model 3D-parallelism training
Agentic components of the Llama Stack APIs
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate, Groq (100+ LLMs)
GPT based autonomous agent that does online comprehensive research on any given topic
Official inference library for Mistral models
LP-MusicCaps: LLM-Based Pseudo Music Captioning [ISMIR23]
An extended project of the LLM Compiler paper, focusing on developing LLM-based Autonomous Agents.
Fast and memory-efficient exact attention
AI model designed to test the effectiveness in handling external ethical attacks.
The official implementation of βSophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-trainingβ
MetricEval: A framework that conceptualizes and operationalizes four main components of metric evaluation, in terms of reliability and validity
Enhanced ChatGPT Clone: Features OpenAI, Assistants API, Azure, Groq, GPT-4 Vision, Mistral, Bing, Anthropic, OpenRouter, Vertex AI, Gemini, AI model switching, message search, langchain, DALL-E-3,β¦
An Analytical Evaluation Board of Multi-turn LLM Agents
Constructing community of LLM-based Agent in the minecraft
llama3.np is a pure NumPy implementation for Llama 3 model.
A modern JavaScript library for handling Hangul characters.
The papers are organized according to our survey: Evaluating Large Language Models: A Comprehensive Survey.