hdmquan / torch_activationLinks
Torch-activation, a library of activation functions for PyTorch library
☆26Updated 6 months ago
Alternatives and similar repositories for torch_activation
Users that are interested in torch_activation are comparing it to the libraries listed below
Sorting:
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆102Updated 10 months ago
- RWKV-7: Surpassing GPT☆98Updated 11 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆110Updated 6 months ago
- ☆136Updated last year
- Collection of autoregressive model implementation☆86Updated 6 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated last year
- DeMo: Decoupled Momentum Optimization☆194Updated 10 months ago
- PyTorch implementation of models from the Zamba2 series.☆185Updated 9 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆107Updated 7 months ago
- ☆62Updated 3 months ago
- ☆81Updated last year
- ☆36Updated 2 months ago
- Alice in Wonderland code base for experiments and raw experiments data☆131Updated last month
- open source alpha evolve☆66Updated 5 months ago
- ☆102Updated 3 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆145Updated 8 months ago
- ☆55Updated 11 months ago
- ☆49Updated 8 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated 3 months ago
- Exploration into the proposed architecture from Sapient Intelligence of Singapore 🇸🇬☆68Updated 2 months ago
- entropix style sampling + GUI☆27Updated 11 months ago
- ☆64Updated 7 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆58Updated last week
- Code for the paper Don't Pay Attention☆50Updated last month
- ☆49Updated 8 months ago
- An introduction to LLM Sampling☆79Updated 10 months ago
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resources☆147Updated 3 weeks ago
- Simple GRPO scripts and configurations.☆59Updated 8 months ago
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆66Updated last year
- ☆57Updated 3 weeks ago