Aleph-Alpha-Research / scalingLinks
Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for training large language models.
☆64Updated last month
Alternatives and similar repositories for scaling
Users that are interested in scaling are comparing it to the libraries listed below
Sorting:
- ☆143Updated 2 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆172Updated 4 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆107Updated 8 months ago
- ☆47Updated last year
- ☆81Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated 3 months ago
- Experiments for efforts to train a new and improved t5☆75Updated last year
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 11 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆173Updated 10 months ago
- A set of Python scripts that makes your experience on TPU better☆54Updated 2 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆151Updated 9 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆110Updated 6 months ago
- Functional Benchmarks and the Reasoning Gap☆89Updated last year
- Code for the paper "Fishing for Magikarp"☆172Updated 6 months ago
- Understand and test language model architectures on synthetic tasks.☆238Updated last month
- A MAD laboratory to improve AI architecture designs 🧪☆133Updated 11 months ago
- some common Huggingface transformers in maximal update parametrization (µP)☆86Updated 3 years ago
- Manage scalable open LLM inference endpoints in Slurm clusters☆276Updated last year
- smolLM with Entropix sampler on pytorch☆150Updated last year
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆87Updated last year
- Code repository for the c-BTM paper☆108Updated 2 years ago
- Collection of autoregressive model implementation☆86Updated 6 months ago
- ☆61Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- DeMo: Decoupled Momentum Optimization☆197Updated 11 months ago
- code for training & evaluating Contextual Document Embedding models☆200Updated 6 months ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆224Updated 2 months ago
- ☆106Updated 3 weeks ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated 2 years ago
- Just a bunch of benchmark logs for different LLMs☆118Updated last year