crowsonkb / dice-mc
DiCE: The Infinitely Differentiable Monte-Carlo Estimator
☆30Updated last year
Related projects ⓘ
Alternatives and complementary repositories for dice-mc
- Latent Diffusion Language Models☆67Updated last year
- Implementation of a holodeck, written in Pytorch☆17Updated last year
- Utilities for PyTorch distributed☆23Updated last year
- ☆16Updated 2 years ago
- Describe the format of image/text datasets☆11Updated 2 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆47Updated 2 years ago
- RWKV model implementation☆38Updated last year
- Automatically take good care of your preemptible TPUs☆32Updated last year
- A scalable implementation of diffusion and flow-matching with XGBoost models, applied to calorimeter data.☆17Updated 2 weeks ago
- ☆31Updated 2 months ago
- FID computation in Jax/Flax.☆24Updated 4 months ago
- Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️☆52Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated 5 months ago
- A JAX nn library☆21Updated 8 months ago
- ☆18Updated last month
- A GPT, made only of MLPs, in Jax☆55Updated 3 years ago
- AdaCat☆49Updated 2 years ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆49Updated 2 years ago
- My explorations into editing the knowledge and memories of an attention network☆34Updated last year
- Implementation of LogAvgExp for Pytorch☆32Updated 2 years ago
- ☆21Updated last year
- Texture mapping with variational auto-encoders☆40Updated 3 years ago
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆49Updated 2 years ago
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbols☆14Updated 3 years ago
- Implementation of Metaformer, but in an autoregressive manner☆23Updated 2 years ago
- ☆33Updated last year