ridgerchu / matmulfreellm
Implementation for MatMul-free LM.
☆2,920Updated 2 weeks ago
Related projects ⓘ
Alternatives and complementary repositories for matmulfreellm
- Efficient Triton Kernels for LLM Training☆3,454Updated this week
- Tile primitives for speedy kernels☆1,658Updated this week
- nanoGPT style version of Llama 3.1☆1,246Updated 3 months ago
- A nanoGPT pipeline packed in a spreadsheet☆2,047Updated 5 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆3,036Updated last week
- NanoGPT (124M) quality in 7.8 8xH100-minutes☆1,033Updated this week
- A native PyTorch Library for large model training☆2,623Updated this week
- The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling☆703Updated 2 months ago
- Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"☆803Updated 3 months ago
- Schedule-Free Optimization in PyTorch☆1,898Updated 2 weeks ago
- PyTorch native quantization and sparsity for training and inference☆1,585Updated this week
- A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!☆3,256Updated 3 months ago
- PyTorch native finetuning library☆4,336Updated this week
- llama3.np is a pure NumPy implementation for Llama 3 model.☆975Updated 5 months ago
- Distributed Training Over-The-Internet☆688Updated 2 months ago
- ☆2,746Updated 2 months ago
- Tools for merging pretrained large language models.☆4,816Updated 2 weeks ago
- UNet diffusion model in pure CUDA☆584Updated 4 months ago
- Go ahead and axolotl questions☆7,930Updated this week
- Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch☆1,692Updated last week
- Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors a…☆1,199Updated this week
- ☆6,781Updated 3 weeks ago
- Blazingly fast LLM inference.☆4,472Updated this week
- MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.☆1,155Updated 2 weeks ago
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,045Updated this week
- 4M: Massively Multimodal Masked Modeling☆1,607Updated last month
- The n-gram Language Model☆1,342Updated 3 months ago
- Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"☆515Updated 4 months ago
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,679Updated this week
- ☆4,035Updated 5 months ago