Binfeng Xu 's Projects
Instruct-tune LLaMA on consumer hardware
Recommender of daily papers from arXiv, customized with your Prompt.
Recommender System Papers
Accessible large language models via k-bit quantization for PyTorch.
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
Self-use Day Trade Alert for Crypto Currency
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
My undergraduate research @ WFU. Innovative approach to preprocess Agent-Interaction Data.
⚡ Building applications with LLMs through composability ⚡
Inference code for LLaMA models
An LLM agent capable of training LLM.
A real chat BOT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Study notes in casual writings.
NYU Deep Learning Spring 2020
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more
Code for Prediction and Planning Under Uncertainty (PPUU)
Decoupling Reasoning from Observations for Efficient Augmented Language Models
High-Resolution Image Synthesis with Latent Diffusion Models
Simplex Quant to beat them all.
Neural Activity Tensor Decomposition and Data Mining; My CS thesis@WFU
Port of OpenAI's Whisper model in C/C++