Junghwan Park's starred repositories
agent-zero
Agent Zero AI framework
ms-swift
Use PEFT or Full-parameter to finetune 350+ LLMs or 90+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL, Phi3.5-Vision, ...)
transformer-explainer
Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization
llm_aided_ocr
Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.
Gradient-Free-Optimizers
Simple and reliable optimization with local, global, population-based and sequential techniques in numerical discrete search spaces.
nano-llama31
nanoGPT style version of Llama 3.1
VideoLLaMA2
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
dom-to-semantic-markdown
DOM to Semantic-Markdown for use with LLMs
ragbuilder
A toolkit to create optimal Production-ready RAG setup for your data
Prompt-BERT
PromptBERT: Improving BERT Sentence Embeddings with Prompts
WebVoyager
Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"
vectorlite
Fast, SQL powered, in-process vector search for any language with an SQLite driver
jekyll-jupyter-notebook
Jekyll Jupyter Notebook plugin
redcache-ai
A memory framework for Large Language Models and Agents.
lmms-finetune
A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, qwen-vl, phi3-v etc.
scaling_sentemb
Scaling Sentence Embeddings with Large Language Models