VatsaDev / NanoPoorLinks
NanoGPT-speedrunning for the poor T4 enjoyers
☆72Updated 6 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)☆107Updated 7 months ago
- Collection of autoregressive model implementation☆86Updated 6 months ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆61Updated this week
- ☆28Updated last year
- H-Net Dynamic Hierarchical Architecture☆80Updated last month
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated 3 months ago
- DeMo: Decoupled Momentum Optimization☆194Updated 10 months ago
- smolLM with Entropix sampler on pytorch☆150Updated 11 months ago
- look how they massacred my boy☆63Updated last year
- An introduction to LLM Sampling☆79Updated 10 months ago
- working implimention of deepseek MLA☆44Updated 9 months ago
- SIMD quantization kernels☆89Updated last month
- NanoGPT (124M) quality in 2.67B tokens☆28Updated last month
- ☆136Updated last year
- Landing repository for the paper "Softpick: No Attention Sink, No Massive Activations with Rectified Softmax"☆85Updated last month
- ☆40Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆58Updated last week
- RWKV-7: Surpassing GPT☆98Updated 11 months ago
- Simple repository for training small reasoning models☆43Updated 8 months ago
- ☆64Updated 7 months ago
- Simple GRPO scripts and configurations.☆59Updated 8 months ago
- rl from zero pretrain, can it be done? yes.☆277Updated 3 weeks ago
- Storing long contexts in tiny caches with self-study☆201Updated last week
- Simple & Scalable Pretraining for Neural Architecture Research☆297Updated 2 months ago
- supporting pytorch FSDP for optimizers☆83Updated 10 months ago
- Simple Transformer in Jax☆139Updated last year
- ☆46Updated 6 months ago
- PyTorch implementation of models from the Zamba2 series.☆185Updated 9 months ago
- ☆91Updated last year
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆103Updated 2 weeks ago