craffel / comp664-deep-learning-spring-2023
Course repository for the Spring 2023 COMP664 course "Deep Learning" at UNC
☆14Updated last year
Related projects: ⓘ
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆31Updated 3 months ago
- ☆14Updated this week
- Implementation of Insertion-deletion Denoising Diffusion Probabilistic Models☆29Updated 2 years ago
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"☆21Updated last week
- Minimum Description Length probing for neural network representations☆15Updated 11 months ago
- Using FlexAttention to compute attention with different masking patterns☆28Updated last week
- ☆29Updated last year
- Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorch☆27Updated this week
- ☆21Updated this week
- ☆19Updated this week
- ☆23Updated this week
- Source-to-Source Debuggable Derivatives in Pure Python☆14Updated 7 months ago
- Training and evaluation code for the paper "Headless Language Models: Learning without Predicting with Contrastive Weight Tying" (https:/…☆22Updated 5 months ago
- ☆22Updated 3 months ago
- Course materials for 11-767☆13Updated last year
- My explorations into editing the knowledge and memories of an attention network☆34Updated last year
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆47Updated 2 years ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆50Updated 2 years ago
- ☆45Updated 7 months ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"☆34Updated 10 months ago
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆33Updated last year
- This repository hosts the code to port NumPy model weights of BiT-ResNets to TensorFlow SavedModel format.☆14Updated 2 years ago
- Few-shot Learning with Auxiliary Data☆26Updated 9 months ago
- This library supports evaluating disparities in generated image quality, diversity, and consistency between geographic regions.☆19Updated 3 months ago
- ☆11Updated this week
- RWKV model implementation☆38Updated last year
- Shows how to do parameter ensembling using differential evolution.☆10Updated 2 years ago
- Directed masked autoencoders☆13Updated last year
- Official implementation of paper "On the Diagram of Thought" (https://arxiv.org/abs/2409.10038)☆32Updated this week