FusionBrainLab / LLM-MicroscopeLinks
☆70Updated last year
Alternatives and similar repositories for LLM-Microscope
Users that are interested in LLM-Microscope are comparing it to the libraries listed below
Sorting:
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆128Updated last year
- Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"☆163Updated 8 months ago
- ☆85Updated last year
- ☆54Updated 6 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated 10 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆129Updated 9 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆82Updated 10 months ago
- ☆82Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆160Updated 2 months ago
- ☆36Updated last week
- ☆87Updated last year
- ☆69Updated last year
- σ-GPT: A New Approach to Autoregressive Models☆67Updated last year
- ☆53Updated last year
- Token Omission Via Attention☆128Updated 11 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- GoldFinch and other hybrid transformer components☆45Updated last year
- Griffin MQA + Hawk Linear RNN Hybrid☆89Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated 11 months ago
- [ICML 24 NGSM workshop] Associative Recurrent Memory Transformer implementation and scripts for training and evaluation☆51Updated 2 weeks ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆101Updated 8 months ago
- ☆57Updated 11 months ago
- ☆102Updated last month
- One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation☆42Updated 11 months ago
- Explorations into the recently proposed Taylor Series Linear Attention☆100Updated last year
- DeMo: Decoupled Momentum Optimization☆190Updated 9 months ago
- Work in progress.☆72Updated 2 months ago
- Mixture of A Million Experts☆47Updated last year
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆67Updated 3 months ago