xjdr-alt / entropix-localLinks
smol models are fun too
☆93Updated last year
Alternatives and similar repositories for entropix-local
Users that are interested in entropix-local are comparing it to the libraries listed below
Sorting:
- smolLM with Entropix sampler on pytorch☆149Updated last year
- Simple Transformer in Jax☆140Updated last year
- Plotting (entropy, varentropy) for small LMs☆99Updated 7 months ago
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆315Updated 6 months ago
- train entropix like a champ!☆20Updated last year
- look how they massacred my boy☆63Updated last year
- ☆131Updated last year
- Fast parallel LLM inference for MLX☆241Updated last year
- MoE training for Me and You and maybe other people☆319Updated last week
- A comprehensive repository of reasoning tasks for LLMs (and beyond)☆455Updated last year
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆61Updated last year
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆109Updated 10 months ago
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆77Updated 11 months ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆183Updated 2 months ago
- Long context evaluation for large language models☆225Updated 10 months ago
- explore token trajectory trees on instruct and base models☆150Updated 7 months ago
- A graph visualization of attention☆57Updated 7 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated last year
- DeMo: Decoupled Momentum Optimization☆198Updated last year
- Train your own SOTA deductive reasoning model☆107Updated 10 months ago
- ☆125Updated last year
- ☆137Updated last year
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆85Updated 4 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated last year
- rl from zero pretrain, can it be done? yes.☆286Updated 3 months ago
- SIMD quantization kernels☆92Updated 4 months ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆174Updated 11 months ago
- ☆334Updated 5 months ago
- Draw more samples☆198Updated last year
- ComplexTensor: Machine Learning By Bridging Classical and Quantum Computation☆78Updated last year