AI-Hypercomputer / RecMLLinks
☆208Updated this week
Alternatives and similar repositories for RecML
Users that are interested in RecML are comparing it to the libraries listed below
Sorting:
- Multi-backend recommender systems with Keras 3☆141Updated 2 weeks ago
- ☆155Updated 9 months ago
- SIMD quantization kernels☆87Updated last week
- High-Performance Engine for Multi-Vector Search☆156Updated last week
- An introduction to LLM Sampling☆79Updated 9 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆291Updated 3 weeks ago
- lossily compress representation vectors using product quantization☆59Updated 4 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorch☆96Updated last month
- XTR/WARP (SIGIR'25) is an extremely fast and accurate retrieval engine based on Stanford's ColBERTv2/PLAID and Google DeepMind's XTR.☆164Updated 4 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆71Updated 4 months ago
- ☆69Updated 2 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆322Updated 10 months ago
- A framework for optimizing DSPy programs with RL☆172Updated this week
- Library for text-to-text regression, applicable to any input string representation and allows pretraining and fine-tuning over multiple r…☆218Updated last week
- Simple UI for debugging correlations of text embeddings☆291Updated 3 months ago
- j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.☆97Updated last month
- code for training & evaluating Contextual Document Embedding models☆197Updated 4 months ago
- smolLM with Entropix sampler on pytorch☆150Updated 10 months ago
- PageRank for LLMs☆50Updated last week
- ☆68Updated 3 months ago
- Train your own SOTA deductive reasoning model☆106Updated 6 months ago
- ☆39Updated last year
- rl from zero pretrain, can it be done? yes.☆268Updated 3 weeks ago
- ☆417Updated 3 weeks ago
- ☆497Updated last month
- ☆210Updated 2 months ago
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆105Updated 6 months ago
- look how they massacred my boy☆64Updated 11 months ago
- Lightweight Nearest Neighbors with Flexible Backends☆300Updated 2 months ago
- ☆239Updated 6 months ago