xjdr-alt / entropix-trainerLinks
train entropix like a champ!
☆20Updated 11 months ago
Alternatives and similar repositories for entropix-trainer
Users that are interested in entropix-trainer are comparing it to the libraries listed below
Sorting:
- look how they massacred my boy☆64Updated 10 months ago
- MLX port for xjdr's entropix sampler (mimics jax implementation)☆62Updated 10 months ago
- Plotting (entropy, varentropy) for small LMs☆98Updated 3 months ago
- smol models are fun too☆93Updated 10 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated 11 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 6 months ago
- smolLM with Entropix sampler on pytorch☆150Updated 10 months ago
- A tree-based prefix cache library that allows rapid creation of looms: hierarchal branching pathways of LLM generations.☆73Updated 7 months ago
- Modify Entropy Based Sampling to work with Mac Silicon via MLX☆49Updated 10 months ago
- Train your own SOTA deductive reasoning model☆106Updated 6 months ago
- SIMD quantization kernels☆86Updated last week
- ☆68Updated 3 months ago
- Synthetic data derived by templating, few shot prompting, transformations on public domain corpora, and monte carlo tree search.☆33Updated 6 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 7 months ago
- Simple Transformer in Jax☆139Updated last year
- NSA Triton Kernels written with GPT5 and Opus 4.1☆65Updated last month
- ☆21Updated 8 months ago
- A simple MLX implementation for pretraining LLMs on Apple Silicon.☆83Updated 3 weeks ago
- ☆39Updated last year
- Approximating the joint distribution of language models via MCTS☆21Updated 10 months ago
- Storing long contexts in tiny caches with self-study☆179Updated last week
- An introduction to LLM Sampling☆79Updated 9 months ago
- ☆133Updated 5 months ago
- ☆27Updated last year
- Compiling useful links, papers, benchmarks, ideas, etc.☆45Updated 5 months ago
- Modded vLLM to run pipeline parallelism over public networks☆39Updated 3 months ago
- PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP☆120Updated this week
- DeMo: Decoupled Momentum Optimization☆190Updated 9 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆71Updated 4 months ago
- ☆13Updated 4 months ago