lucidrains / HRMLinks
Exploration into the proposed architecture from Sapient Intelligence of Singapore πΈπ¬
β63Updated last month
Alternatives and similar repositories for HRM
Users that are interested in HRM are comparing it to the libraries listed below
Sorting:
- β134Updated last year
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokensβ146Updated 7 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.β322Updated 11 months ago
- β102Updated last month
- The simplest, fastest repository for training/finetuning medium-sized xLSTMs.β41Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.β172Updated 8 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)β105Updated 6 months ago
- look how they massacred my boyβ64Updated 11 months ago
- smolLM with Entropix sampler on pytorchβ150Updated 10 months ago
- EvaByte: Efficient Byte-level Language Models at Scaleβ109Updated 5 months ago
- PyTorch implementation of models from the Zamba2 series.β185Updated 7 months ago
- Train your own SOTA deductive reasoning modelβ106Updated 6 months ago
- Plotting (entropy, varentropy) for small LMsβ98Updated 4 months ago
- Implementation snake game based on Diffusion modelβ91Updated 8 months ago
- Simple GRPO scripts and configurations.β59Updated 7 months ago
- RWKV-7: Surpassing GPTβ95Updated 10 months ago
- NanoGPT-speedrunning for the poor T4 enjoyersβ71Updated 5 months ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the userβ¦β180Updated 2 months ago
- smol models are fun tooβ93Updated 10 months ago
- Alice in Wonderland code base for experiments and raw experiments dataβ131Updated this week
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"β101Updated 9 months ago
- run paligemma in real timeβ132Updated last year
- Code for ExploreTomβ86Updated 2 months ago
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for trβ¦β65Updated 10 months ago
- Low-Rank adapter extraction for fine-tuned transformers modelsβ177Updated last year
- GRadient-INformed MoEβ264Updated 11 months ago
- β120Updated 8 months ago
- Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"β163Updated 8 months ago
- Video+code lecture on building nanoGPT from scratchβ69Updated last year
- Automated Capability Discovery via Foundation Model Self-Explorationβ63Updated 7 months ago