idiap / sigma-gptLinks
σ-GPT: A New Approach to Autoregressive Models
☆68Updated last year
Alternatives and similar repositories for sigma-gpt
Users that are interested in sigma-gpt are comparing it to the libraries listed below
Sorting:
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- ☆53Updated last year
- ☆82Updated last year
- ☆89Updated last year
- Implementation of the Llama architecture with RLHF + Q-learning☆168Updated 8 months ago
- Focused on fast experimentation and simplicity☆75Updated 9 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆102Updated 9 months ago
- Collection of autoregressive model implementation☆86Updated 5 months ago
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆146Updated this week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆164Updated 3 months ago
- DeMo: Decoupled Momentum Optimization☆193Updated 10 months ago
- ☆55Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 7 months ago
- ☆28Updated last year
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆223Updated last year
- ☆62Updated last year
- H-Net Dynamic Hierarchical Architecture☆80Updated 3 weeks ago
- WIP☆93Updated last year
- supporting pytorch FSDP for optimizers☆84Updated 9 months ago
- ☆63Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- A MAD laboratory to improve AI architecture designs 🧪☆129Updated 9 months ago
- ☆34Updated last year
- ☆58Updated last year
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- ☆102Updated 2 months ago
- ☆24Updated 4 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 10 months ago
- research impl of Native Sparse Attention (2502.11089)☆61Updated 7 months ago
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆65Updated this week