microsoft / GRIN-MoELinks
GRadient-INformed MoE
☆264Updated 11 months ago
Alternatives and similar repositories for GRIN-MoE
Users that are interested in GRIN-MoE are comparing it to the libraries listed below
Sorting:
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆293Updated 3 weeks ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆201Updated last year
- EvaByte: Efficient Byte-level Language Models at Scale☆109Updated 4 months ago
- Code for ExploreTom☆86Updated 2 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆124Updated last month
- ☆134Updated last year
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆343Updated 9 months ago
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆88Updated 4 months ago
- PyTorch implementation of models from the Zamba2 series.☆185Updated 7 months ago
- accompanying material for sleep-time compute paper☆111Updated 4 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆146Updated 7 months ago
- ☆133Updated 6 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆95Updated this week
- ☆175Updated last month
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆245Updated 7 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆322Updated 10 months ago
- ☆119Updated last year
- All information and news with respect to Falcon-H1 series☆88Updated last month
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆340Updated 2 months ago
- RWKV-7: Surpassing GPT☆95Updated 10 months ago
- ☆124Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 6 months ago
- Official repo for "Make Your LLM Fully Utilize the Context"☆254Updated last year
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆96Updated last month
- ☆91Updated 3 months ago
- Train your own SOTA deductive reasoning model☆106Updated 6 months ago
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆116Updated last month
- ☆155Updated 5 months ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆249Updated last year