microsoft / ArchScaleLinks
Simple & Scalable Pretraining for Neural Architecture Research
☆299Updated 2 weeks ago
Alternatives and similar repositories for ArchScale
Users that are interested in ArchScale are comparing it to the libraries listed below
Sorting:
- EvaByte: Efficient Byte-level Language Models at Scale☆110Updated 6 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 10 months ago
- Storing long contexts in tiny caches with self-study☆216Updated last month
- PyTorch implementation of models from the Zamba2 series.☆185Updated 9 months ago
- rl from zero pretrain, can it be done? yes.☆280Updated last month
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆82Updated 8 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆107Updated 8 months ago
- Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…☆356Updated 11 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆111Updated last month
- Dion optimizer algorithm☆384Updated this week
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆129Updated 3 months ago
- PyTorch building blocks for the OLMo ecosystem☆319Updated this week
- code for training & evaluating Contextual Document Embedding models☆200Updated 6 months ago
- Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research☆259Updated this week
- All information and news with respect to Falcon-H1 series☆93Updated last month
- Memory optimized Mixture of Experts☆69Updated 3 months ago
- PyTorch-native post-training at scale☆532Updated this week
- Library for text-to-text regression, applicable to any input string representation and allows pretraining and fine-tuning over multiple r…☆287Updated this week
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆346Updated 6 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆249Updated 9 months ago
- Super basic implementation (gist-like) of RLMs with REPL environments.☆248Updated last month
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆303Updated 2 weeks ago
- An extension of the nanoGPT repository for training small MOE models.☆212Updated 8 months ago
- Train your own SOTA deductive reasoning model☆107Updated 8 months ago
- GRadient-INformed MoE☆264Updated last year
- Training-Ready RL Environments + Evals☆174Updated this week
- This repo contains the source code for the paper "Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning"☆255Updated this week
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆301Updated this week
- ☆200Updated 11 months ago
- Normalized Transformer (nGPT)☆192Updated last year