evanatyourservice / llm-jaxLinks
Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.
☆18Updated 3 months ago
Alternatives and similar repositories for llm-jax
Users that are interested in llm-jax are comparing it to the libraries listed below
Sorting:
- ☆46Updated last year
- ☆81Updated last year
- Collection of autoregressive model implementation☆86Updated 6 months ago
- ☆19Updated 5 months ago
- train with kittens!☆63Updated last year
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆64Updated 3 weeks ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆72Updated 6 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆102Updated 10 months ago
- Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.☆32Updated 4 months ago
- Latent Large Language Models☆19Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆107Updated 7 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- ☆50Updated last year
- ☆28Updated last year
- ☆15Updated last year
- GoldFinch and other hybrid transformer components☆45Updated last year
- ☆86Updated last year
- NanoGPT (124M) quality in 2.67B tokens☆28Updated last month
- ☆91Updated last year
- ☆53Updated last year
- H-Net Dynamic Hierarchical Architecture☆80Updated last month
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28Updated 5 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆58Updated last week
- ☆65Updated 7 months ago
- supporting pytorch FSDP for optimizers☆83Updated 10 months ago
- A set of Python scripts that makes your experience on TPU better☆54Updated last month
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- Experiments for efforts to train a new and improved t5☆75Updated last year
- some common Huggingface transformers in maximal update parametrization (µP)☆86Updated 3 years ago
- ☆20Updated 2 years ago