nreHieW / lossLinks
Visualising Losses in Deep Neural Networks
☆16Updated last year
Alternatives and similar repositories for loss
Users that are interested in loss are comparing it to the libraries listed below
Sorting:
- ☆24Updated 11 months ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆55Updated 8 months ago
- A dashboard for exploring timm learning rate schedulers☆19Updated last year
- Implementation of a Light Recurrent Unit in Pytorch☆49Updated last year
- Implementation of a holodeck, written in Pytorch☆18Updated 2 years ago
- Collection of autoregressive model implementation☆85Updated 7 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆103Updated 11 months ago
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 10 months ago
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data☆23Updated last year
- Explorations into adversarial losses on top of autoregressive loss for language modeling☆38Updated 9 months ago
- Experimental scripts for researching data adaptive learning rate scheduling.☆22Updated 2 years ago
- Local Attention - Flax module for Jax☆22Updated 4 years ago
- Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto☆57Updated last year
- Utilities for PyTorch distributed☆25Updated 9 months ago
- Exploration into the Scaling Value Iteration Networks paper, from Schmidhuber's group☆37Updated last year
- Utilities for Training Very Large Models☆58Updated last year
- JAX Scalify: end-to-end scaled arithmetics☆17Updated last year
- Implementation of 2-simplicial attention proposed by Clift et al. (2019) and the recent attempt to make practical in Fast and Simplex, Ro…☆47Updated 3 months ago
- Load any clip model with a standardized interface☆22Updated last month
- Some personal experiments around routing tokens to different autoregressive attention, akin to mixture-of-experts☆120Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated last year
- Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.☆22Updated 2 years ago
- Little article showing how to load pytorch's models with linear memory consumption☆34Updated 3 years ago
- My explorations into editing the knowledge and memories of an attention network☆35Updated 2 years ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Implementation of the proposed Spline-Based Transformer from Disney Research☆105Updated last year
- ☆21Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆77Updated last week
- ResiDual: Transformer with Dual Residual Connections, https://arxiv.org/abs/2304.14802☆96Updated 2 years ago