π TPTT: Transforming Pretrained Transformers into Titans
β66Jun 7, 2026Updated 4 months ago
Alternatives and similar repositories for tptt
Users that are interested in tptt are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Unofficial Implementation of Titans: Learning to Memorize at Test Timeβ12Mar 16, 2025Updated last year
- Adaptation of titans-pytorch to llama models on HFβ26Mar 6, 2025Updated last year
- Official Repo for Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamicsβ80Sep 25, 2026Updated last month
- β72Jul 8, 2025Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Schedulingβ44Dec 29, 2025Updated 10 months ago
- 1-Click AI Models by DigitalOcean Gradient β’ AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- β17Dec 19, 2024Updated last year
- Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Realityβ364Aug 21, 2026Updated 2 months ago
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Ruleβ691Mar 13, 2026Updated 7 months ago
- This repository, deepspeed-grpo-qlora-vllm, provides a complete framework for fine-tuning LLMs using Group Relative Policy Optimization (β¦β13Jul 15, 2025Updated last year
- β142Jun 6, 2025Updated last year
- β149Feb 4, 2026Updated 8 months ago
- Code release for paper "Test-Time Training Done Right"β536Jan 5, 2026Updated 9 months ago
- Official code for the NeurIPS25 paper "RAT: Bridging RNN Efficiencyand Attention Accuracy in Language Modeling" (https://arxiv.org/abs/25β¦β26Aug 31, 2026Updated 2 months ago
- π₯ A minimal training framework for scaling FLA modelsβ425Apr 22, 2026Updated 6 months ago
- 1-Click AI Models by DigitalOcean Gradient β’ AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- I seek to draw from the philosophies embedded in AI research to inspire deeper reflection on life β exploring how the principles that guiβ¦β13Aug 11, 2025Updated last year
- [COLM 2026] Resa: Transparent Reasoning Models via SAEsβ49Sep 23, 2025Updated last year
- β14Jun 24, 2024Updated 2 years ago
- β20Sep 6, 2025Updated last year
- VibeRL is a Reinforcement Learning framework built essentially through vibe coding with Kimi K2.β18Oct 26, 2026Updated last week
- An efficient implementation of the NSA (Native Sparse Attention) kernelβ135Jun 24, 2025Updated last year
- Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining itsβ¦β22Sep 10, 2024Updated 2 years ago
- Delta Attention Residuals - supplementary code and pretrained modelsβ45Sep 26, 2026Updated last month
- β13Apr 15, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer β’ AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Zoof is a high-efficiency Small Language Model (SLM) engineered from scratch. It demonstrates how modern architectural choices and high-qβ¦β48Jan 13, 2026Updated 9 months ago
- Memory optimized Mixture of Expertsβ84Jul 25, 2025Updated last year
- Code: Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data (ICML2025)β13May 9, 2025Updated last year
- Transforms raw text into interconnected knowledge graphs and autonomously generates insights through advanced pattern detection. It combiβ¦β11Jul 29, 2026Updated 3 months ago
- A linker for partial GPU kernels.β44Updated this week
- EvaByte: Efficient Byte-level Language Models at Scaleβ120Apr 22, 2025Updated last year
- A multi-agent system built with DSPy that coordinates research and writing agents to produce comprehensive articles on any topic.β13Aug 3, 2025Updated last year
- β69Aug 29, 2024Updated 2 years ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsβ¦β386Dec 12, 2024Updated last year
- End-to-end encrypted email - Proton Mail β’ AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- continous batching and parallel acceleration for RWKV6β23Jun 28, 2024Updated 2 years ago
- Use Blender for figures.β15Feb 11, 2026Updated 8 months ago
- ζ On-Policy Distillation ζ₯ε° DSparkγβ19Jun 28, 2026Updated 4 months ago
- Code and data for Character-level Chinese-English Translation through ASCII Encodingβ13Oct 31, 2018Updated 8 years ago
- Official JAX implementation of End-to-End Test-Time Training for Long Contextβ715Feb 15, 2026Updated 8 months ago
- β10Nov 9, 2023Updated 2 years ago
- Official implementation of the ΞBelief-RL method.β32Feb 28, 2026Updated 8 months ago