mixedbread-ai / ofen
WIP: Ofen is a toolkit aimed at making transformer models production-ready. API included
☆14Updated 5 months ago
Alternatives and similar repositories for ofen:
Users that are interested in ofen are comparing it to the libraries listed below
- Showcase how mxbai-embed-large-v1 can be used to produce binary embedding. Binary embeddings enabled 32x storage savings and 40x faster r…☆15Updated last year
- Crispy reranking models by Mixedbread☆19Updated last week
- ANE accelerated embedding models!☆17Updated 3 months ago
- The Batched API provides a flexible and efficient way to process multiple requests in a batch, with a primary focus on dynamic batching o…☆126Updated 3 months ago
- Training hybrid models for dummies.☆20Updated 2 months ago
- implementation of https://arxiv.org/pdf/2312.09299☆20Updated 8 months ago
- Latent Large Language Models☆17Updated 7 months ago
- NLP with Rust for Python 🦀🐍☆61Updated 9 months ago
- ☆49Updated last year
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆173Updated 6 months ago
- mixedbread ai python sdk☆11Updated 8 months ago
- Pre-train Static Word Embeddings☆50Updated 3 weeks ago
- ☆43Updated last month
- GPU accelerated client-side embeddings for vector search, RAG etc.☆66Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆39Updated last month
- A clone of OpenAI's Tokenizer page for HuggingFace Models☆45Updated last year
- Training code for Sparse Autoencoders on Embedding models☆36Updated last month
- Zeta implementation of a reusable and plug in and play feedforward from the paper "Exponentially Faster Language Modeling"☆15Updated 4 months ago
- GGML implementation of BERT model with Python bindings and quantization.☆56Updated last year
- Efficiently computing & storing token n-grams from large corpora☆19Updated 5 months ago
- utilities for loading and running text embeddings with onnx☆44Updated 7 months ago
- Tokun to can tokens☆16Updated last month
- Hugging Face Inference Toolkit used to serve transformers, sentence-transformers, and diffusers models.☆66Updated this week
- wasm bindings for huggingface tokenizers library☆34Updated 2 years ago
- One Line To Build Zero-Data Classifiers in Minutes☆36Updated 6 months ago
- Training and evaluation code for the paper "Headless Language Models: Learning without Predicting with Contrastive Weight Tying" (https:/…☆26Updated 11 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- Fast and versatile tokenizer for language models, compatible with SentencePiece, Tokenizers, Tiktoken and more. Supports BPE, Unigram and…☆19Updated last week
- new optimizer☆19Updated 7 months ago
- Truly flash T5 realization!☆64Updated 10 months ago