Bryce

@BryceMeng · User

GitHub profile ↗ · Compare

There is only one heroism in the world: to see the world as it is and to love it

NYITVancouver39 followers29 repositories

Repositories

BryceMeng/andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

★ 0Forks 0

BryceMeng/Customer-service-AI-agent

A proof-of-concept showing how to build an AI-powered customer service agent using Claude, MCP tools, and a deterministic state machine to automate refund decisions.

★ 0PythonForks 2

BryceMeng/ProbIoU-Sliced

A CV project for efficient GPU-friendly computation of Probabilistic IoU (ProbIoU) used in object detection. Implements sliced (shard-based) batch processing to handle massive bounding boxes without GPU memory overflow.

★ 0PythonForks 0

BryceMeng/CTX-Translator

Understands word sense by context and idioms naturally. CTX-Translator is a LoRA fine-tuned English-to-Chinese translation model.

★ 0PythonForks 0

BryceMeng/AsyncNMultithread

Source code accompanying a series of articles on asynchronous and multithreaded programming.

★ 0JavaScriptForks 0

BryceMeng/BabelDOC

BabelDoc translates English PDFs into Chinese PDFs using LLMs. I improved the prompt so that when using a local small model, the translation error rate dropped from 30% to 3%.

★ 0PythonForks 0

BryceMeng/mlfinlab

MlFinLab helps portfolio managers and traders who want to leverage the power of machine learning by providing reproducible, interpretable, and easy to use tools.

★ 0Forks 0

BryceMeng/arbitragelab

ArbitrageLab is a python library that enables traders who want to exploit mean-reverting portfolios by providing a complete set of algorithms from the best academic journals.

★ 0Forks 0

BryceMeng/FinRL-Library

A Deep Reinforcement Learning Library for Automated Trading in Quantitative Finance. NeurIPS 2020.

★ 0Forks 0

BryceMeng/nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

★ 0Forks 0

BryceMeng/stockpredictionai

In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.

★ 0Forks 0

BryceMeng/stockstats

Supply a wrapper ``StockDataFrame`` based on the ``pandas.DataFrame`` with inline stock statistics/indicators support.

★ 0PythonForks 1