johnma2006 / candle
Deep learning library implemented from scratch in numpy. Mixtral, Mamba, LLaMA, GPT, ResNet, and other experiments.
☆48Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for candle
- Understand and test language model architectures on synthetic tasks.☆162Updated 6 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆84Updated last week
- Normalized Transformer (nGPT)☆66Updated this week
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆214Updated 3 months ago
- Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…☆78Updated 2 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆104Updated last month
- RWKV, in easy to read code☆55Updated this week
- Griffin MQA + Hawk Linear RNN Hybrid☆85Updated 6 months ago
- Implementation of the Llama architecture with RLHF + Q-learning☆157Updated 10 months ago
- Accelerated First Order Parallel Associative Scan☆163Updated 3 months ago
- ☆35Updated 7 months ago
- ☆76Updated 7 months ago
- Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead☆109Updated last week
- A MAD laboratory to improve AI architecture designs 🧪☆95Updated 6 months ago
- Annotated version of the Mamba paper☆457Updated 8 months ago
- ☆73Updated 4 months ago
- ☆49Updated 8 months ago
- A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIM☆50Updated 7 months ago
- Evaluating the Mamba architecture on the Othello game☆43Updated 6 months ago
- Implementation of Infini-Transformer in Pytorch☆104Updated last month
- ☆53Updated 10 months ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆49Updated last year
- Fast modular code to create and train cutting edge LLMs☆65Updated 6 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆86Updated 5 months ago
- A byte-level decoder architecture that matches the performance of tokenized Transformers.☆59Updated 6 months ago
- some common Huggingface transformers in maximal update parametrization (µP)☆76Updated 2 years ago
- Token Omission Via Attention☆120Updated last month
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆119Updated 3 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆177Updated last month
- This is the code that went into our practical dive using mamba as information extraction☆50Updated 10 months ago