- Seoul, Republic of Korea
- sooftware.io
- sooftware95
- in/Soo-hwan
Highlights
- Pro
Lists (2)
Sort Newest
Stars
🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
Universal cross-platform tokenizers binding to HF and sentencepiece
Utilities intended for use with Llama models.
TensorDict is a pytorch dedicated tensor container.
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
A Streamlit component to render ECharts.
Agentic components of the Llama Stack APIs
Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capa…
check daily and per period gpu util and send to slack/teams webhook
AI model designed to test the effectiveness in handling external ethical attacks.
Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]
It lets you connect your streamlit application to a pre-built and secure Login/ Sign-Up page.
SimPO: Simple Preference Optimization with a Reference-Free Reward
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
User-friendly WebUI for AI (Formerly Ollama WebUI)
Custom tabs for on hover streamlit navigation bar created by custom css
A library to create multi-page Streamlit applications with ease.
llama3 implementation one matrix multiplication at a time