unum-cloud / uform
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and π video, up to 5x faster than OpenAI CLIP and LLaVA πΌοΈ & ποΈ
β1,101Updated 2 months ago
Alternatives and similar repositories for uform:
Users that are interested in uform are comparing it to the libraries listed below
- β707Updated last year
- CLIP inference in plain C/C++ with no extra dependenciesβ486Updated 7 months ago
- Fine-tune mistral-7B on 3090s, a100s, h100sβ709Updated last year
- TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbonesβ1,267Updated 11 months ago
- Fast Open-Source Search & Clustering engine Γ for Vectors & π Strings Γ in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, Cβ¦β2,606Updated last month
- Automatically create Faiss knn indices with the most optimal similarity search parameters.β843Updated 10 months ago
- Python bindings for the Transformer models implemented in C/C++ using GGML library.β1,853Updated last year
- π€ A PyTorch library of curated Transformer models and their composable componentsβ883Updated 11 months ago
- The repository for the code of the UltraFastBERT paperβ517Updated last year
- Exact structure out of any language model completion.β507Updated last year
- 4M: Massively Multimodal Masked Modelingβ1,701Updated 2 weeks ago
- [ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddingsβ1,925Updated 2 months ago
- A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for varioβ¦β1,009Updated 3 weeks ago
- Collections of vector search related libraries, service and research papersβ1,472Updated 7 months ago
- Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-β¦β3,328Updated last month
- C++ implementation for BLOOMβ809Updated last year
- Fast, Accurate, Lightweight Python library to make State of the Art Embeddingβ1,882Updated this week
- Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpaliβ1,924Updated last week
- Blazing fast framework for fine-tuning similarity learning modelsβ656Updated 2 months ago
- A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machineβ830Updated last week
- Llama 2 Everywhere (L2E)β1,516Updated 2 months ago
- Training LLMs with QLoRA + FSDPβ1,464Updated 4 months ago
- Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.β685Updated 7 months ago
- Inference code for Persimmon-8Bβ415Updated last year
- ICLR2024 Spotlight: curation/training code, metadata, distribution and pre-trained models for MetaCLIP; CVPR 2024: MoDE: CLIP Data Expertβ¦β1,371Updated last week
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.β1,345Updated this week
- β942Updated last month
- Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.β853Updated last year
- Tune any FALCON in 4-bitβ466Updated last year
- A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.β2,842Updated last year