fangyuan-ksgk

AI Engineer (LLM) @Temus || Artificial Intelligence Student @Stanford

@Temus-AISingapore

Pinned Repositories

auto-test
Automatic Chat with LLM & Test
Language:Python2 3 02
CoT-Reasoning-without-Prompting
Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting
Language:Jupyter Notebook17 1 00
Evolutionary-Model-Merge
Unofficial Implementation of Evolutionary Model Merging
Language:Python33 5 12
llama3-sft
Supervised FineTuning with Llama-3
Language:Jupyter Notebook3 1 00
Mini-LLaVA
A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.
Language:Python84 3 08
paper-read-2024-Jan-Apr
Paper reading run from 17. Jan 2024 - 17. Apr 2024
4 1 00
repo-viewer
Visualize any repo or codebase into diagram or animation
Language:Python101
selective-attention-transformer
Unofficial Implementation of Selective Attention Transformer
Language:Python9 2 10
STaR
Implementation of STaR: Bootstrapping Reasoning With Reasoning
Language:Python40
surfer
Voice Interface on Web Browsing
Language:Python2 2 01

fangyuan-ksgk's Repositories

fangyuan-ksgk/repo-viewer
Visualize any repo or codebase into diagram or animation
Language:Python101
fangyuan-ksgk/selective-attention-transformer
Unofficial Implementation of Selective Attention Transformer
Language:Python9 2 10
fangyuan-ksgk/diamond
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
Language:Python1
fangyuan-ksgk/heuristic-search
Minimal Implmenetation of Evolution of Heuristic, originally used for algorithm search, extended for more general purpose goal-oriented idea search.
Language:Python1 1 0
fangyuan-ksgk/process-supervision
Experiments with Procedure Supervision
Language:Jupyter Notebook1
fangyuan-ksgk/thought-compiler
Agent to help us in research
Language:Jupyter Notebook1 1 0
fangyuan-ksgk/adaptive-length-tokenizer
Adaptive Length Image Tokenization via Recurrent Allocation | How many tokens is an image worth ?
fangyuan-ksgk/agent.exe
fangyuan-ksgk/bolt.new
Prompt, run, edit, and deploy full-stack web applications
fangyuan-ksgk/diffuse-experiment
Experiment on Diffusion world model
Language:Python
fangyuan-ksgk/distill-experiment
Experiment on distillation
Language:Jupyter Notebook
fangyuan-ksgk/Emu3
Next-Token Prediction is All You Need
fangyuan-ksgk/experiment-game
Attempts to build open-sourced version of GameNGen.
fangyuan-ksgk/experiment-idea
Some random idea
Language:Jupyter Notebook
fangyuan-ksgk/fangyuan-ksgk
github page
1 0
fangyuan-ksgk/game-of-life
Simple Python implementation of Conway's game of life and other cellular automata, computed using numpy.fft
Language:Python
fangyuan-ksgk/kotaemon
An open-source RAG-based tool for chatting with your documents.
fangyuan-ksgk/lingua
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
fangyuan-ksgk/ml-ferret
Fork of UI-MLLM implementation from Apple
fangyuan-ksgk/modded-nanogpt
NanoGPT (124M) quality in 2.67B tokens
fangyuan-ksgk/MultiUI
Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding
fangyuan-ksgk/OmniParser
Representation on UI components, useful for downstream task with UI interaction
fangyuan-ksgk/open-canvas
fangyuan-ksgk/open-oasis
Inference script for Oasis 500M
fangyuan-ksgk/Pyramid-Flow
Code of Pyramidal Flow Matching for Efficient Video Generative Modeling
fangyuan-ksgk/screenshot-to-code
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
fangyuan-ksgk/shortcut-models
One-step diffusion fork (also learning on JAX a bit I guess)
fangyuan-ksgk/soar
Code release for paper "Autonomous Improvement of Instruction Following Skills via Foundation Models" | CoRL 2024
fangyuan-ksgk/SUPE
This code accompanies the paper "Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration."
fangyuan-ksgk/tiktok-clone
Language:TypeScript