VatsaDev / NanoPoorLinks
NanoGPT-speedrunning for the poor T4 enjoyers
☆69Updated 4 months ago
Alternatives and similar repositories for NanoPoor
Users that are interested in NanoPoor are comparing it to the libraries listed below
Sorting:
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 5 months ago
- Collection of autoregressive model implementation☆86Updated 4 months ago
- working implimention of deepseek MLA☆43Updated 7 months ago
- Lego for GRPO☆28Updated 3 months ago
- H-Net Dynamic Hierarchical Architecture☆77Updated last month
- An introduction to LLM Sampling☆79Updated 8 months ago
- ☆27Updated last year
- ☆134Updated last year
- DeMo: Decoupled Momentum Optimization☆190Updated 8 months ago
- smolLM with Entropix sampler on pytorch☆150Updated 9 months ago
- Simple GRPO scripts and configurations.☆59Updated 6 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 6 months ago
- rl from zero pretrain, can it be done? yes.☆257Updated this week
- ☆61Updated 5 months ago
- look how they massacred my boy☆64Updated 10 months ago
- ☆49Updated last year
- Simple Transformer in Jax☆139Updated last year
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 2 weeks ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆19Updated last month
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆84Updated this week
- Simple repository for training small reasoning models☆37Updated 6 months ago
- ☆101Updated last month
- ☆82Updated last year
- supporting pytorch FSDP for optimizers☆84Updated 8 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆97Updated 3 weeks ago
- Storing long contexts in tiny caches with self-study☆140Updated this week
- Tiled Flash Linear Attention library for fast and efficient mLSTM Kernels.☆69Updated last week
- ☆39Updated last year
- Simple & Scalable Pretraining for Neural Architecture Research☆289Updated this week
- LLM training in simple, raw C/CUDA☆15Updated 8 months ago