wolfecameron / nanoMoE
An extension of the nanoGPT repository for training small MOE models.
☆140Updated 2 months ago
Alternatives and similar repositories for nanoMoE
Users that are interested in nanoMoE are comparing it to the libraries listed below
Sorting:
- ☆184Updated 3 months ago
- minimal GRPO implementation from scratch☆88Updated 2 months ago
- PyTorch building blocks for the OLMo ecosystem☆210Updated this week
- A repository to unravel the language of GPUs, making their kernel conversations easy to understand☆180Updated this week
- Understand and test language model architectures on synthetic tasks.☆195Updated 2 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆244Updated this week
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆323Updated 5 months ago
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆294Updated last week
- Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch☆166Updated 4 months ago
- code for training & evaluating Contextual Document Embedding models☆184Updated this week
- A project to improve skills of large language models☆367Updated this week
- Normalized Transformer (nGPT)☆176Updated 5 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆120Updated this week
- nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)☆103Updated this week
- ☆163Updated 4 months ago
- Experiments on Multi-Head Latent Attention☆89Updated 8 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆231Updated 3 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆115Updated 4 months ago
- ☆187Updated this week
- ☆176Updated 5 months ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.☆352Updated this week
- ☆50Updated 6 months ago
- Code for studying the super weight in LLM☆100Updated 5 months ago
- BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.☆200Updated last week
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆105Updated this week
- A simplified implementation for experimenting with Reinforcement Learning (RL) on GSM8K, inspired by RLVR and Deepseek R1. This repositor…☆87Updated 3 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆131Updated 9 months ago
- Tina: Tiny Reasoning Models via LoRA☆192Updated 3 weeks ago
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆445Updated last month
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆123Updated 8 months ago