Sungju Kim's starred repositories
excalidraw
Virtual whiteboard for sketching hand-drawn like diagrams
Deep-Live-Cam
real time face swap and one-click video deepfake with only a single image
pytorch-examples
Simple examples to introduce PyTorch
llm-foundry
LLM training code for Databricks foundation models
llama-agentic-system
Agentic components of the Llama Stack APIs
Liger-Kernel
Efficient Triton Kernels for LLM Training
direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
DeepSeek-Coder-V2
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
code-interpreter
Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app
persona-hub
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
system-2-research
System 2 Reasoning Link Collection
text-dedup
All-in-one text de-duplication
safety-rbr-code-and-data
Code and example data for the paper: Rule Based Rewards for Language Model Safety
screen_annotation
The Screen Annotation dataset consists of pairs of mobile screenshots and their annotations. The annotations are in text format, and describe the UI elements present on the screen: their type, location, OCR text and a short description. It has been introduced in the paper `ScreenAI: A Vision-Language Model for UI and Infographics Understanding`.
aider-swe-bench
Harness used to benchmark aider against SWE Bench benchmarks