Matryoshka Multimodal Models
-
Updated
Jan 22, 2025 - Python
#
matryoshka
Here are 26 public repositories matching this topic...
Code and pretrained models for the paper: "MatMamba: A Matryoshka State Space Model"
-
Updated
Nov 21, 2024 - Python
Arabic document search with Matryoshka embeddings, source-linked results, and a Saudi-inspired interface.
embeddings arabic semantic-search arabic-nlp arabic-language document-search fastapi matryoshka sentence-transformers
-
Updated
Sep 7, 2026 - Python
Jina CLIP v2 - Multimodal embedding model for text and images with Matryoshka representations (64-1024 dimensions). Deployed on Replicate with optimized GPU inference.
nlp computer-vision cog transformers pytorch clip replicate image-embeddings text-embeddings matryoshka multimodal-embeddings jina-clip
-
Updated
Sep 5, 2025 - Python
Fine-tune single-vector embeddings on Apple Silicon with MLX: LoRA/QLoRA, GradCache, multi-positive training and teacher ranking distillation.
metal retrieval embeddings lora knowledge-distillation mlx sentence-embeddings fine-tuning hard-negative-mining matryoshka contrastive-learning apple-silicon qlora bge-m3 modernbert gradcache multi-positive-training
-
Updated
Oct 12, 2026 - Python
MCP server for Matryoshka Mind Map — read and write your nested mind maps / TODOs from AI agents
-
Updated
Oct 29, 2026 - TypeScript
Pre-fitted ZCA whitening backgrounds for Qwen/Qwen3-Embedding-4B on Polish text (Wikipedia + mC4 + KLEJ + OASST). Drop-in numpy artefacts; PL/EN docs.
-
Updated
Jul 23, 2026 - Python
Vector infrastructure and Matryoshka embeddings for AI agents
-
Updated
Apr 20, 2026 - TypeScript
🪆 Российская платформа автономных AI-агентов. Импортозамещение ChatGPT одобрено Министерством Цифрового Развития*
-
Updated
Mar 22, 2026 - TypeScript
Practical EmbeddingGemma 2 notebook: multimodal embeddings, semantic search over images, audio and text, Matryoshka dimensions, sentence-transformers
embeddings semantic-search gemma multimodal rag huggingface matryoshka sentence-transformers embeddinggemma embeddinggemma2
-
Updated
Oct 16, 2026 - Jupyter Notebook
Sample introduction to recursive schemes and matryoshka (Library that specializes on implementing recursion schemes on fixed-point types of recursive structures.)
-
Updated
Apr 26, 2022 - Scala
Production embedding & decision inference service in Rust — Candle/ONNX dual engine, CUDA/Metal acceleration, REST/gRPC/MCP/CLI generated via sdforge, rerank, Matryoshka dimensions, OpenAI-compatible API, and semantic caching
rust metal mcp cuda grpc inference embeddings candle onnx vector-search matryoshka batch-inference semantic-cache rerank openai-compatible
-
Updated
Oct 26, 2026 - Rust
High-performance, self-contained Rust inference engine for Google's EmbeddingGemma 2 on Metal, Apple Neural Engine, and CPU SIMD.
audio rust metal embeddings simd vision ane candle gemma inference-engine coreml multimodal rag matryoshka apple-silicon apple-neural-engine gguf embeddinggemma-2
-
Updated
Oct 22, 2026 - Rust
🖼️ Generate high-quality multimodal embeddings for text and images with Jina CLIP v2, offering flexible dimensions and optimized performance for diverse applications.
nlp computer-vision cog transformers pytorch clip replicate image-embeddings text-embeddings matryoshka multimodal-embeddings jina-clip
-
Updated
Oct 14, 2026 - Python
SMAI Project. Made an abstractive qa RAG chatbot using Langchain and experimented with variety of vector stores and retrievers and evaluated them using Ragas
-
Updated
Jun 2, 2024 - Jupyter Notebook
Unified multimodal embedding + retrieval framework (EmbeddingGemma 2 direction): one 768-dim space for text/code/image/audio, Matryoshka any-width embeddings, ColBERT late interaction, INT4 on-device quantization. Zero-dependency.
python machine-learning deep-learning retrieval embeddings zero-dependency quantization multimodal rag matryoshka late-interaction
-
Updated
Oct 8, 2026 - Python
🐱 雨晴向量 — 纯离线 Android 本地文本向量化服务器，跑 EmbeddingGemma 模型，广播 OpenAI 兼容 API | RainyEmbedding - Offline text embedding server on Android
android kotlin machine-learning offline semantic-search embedding nanohttpd on-device litert privacy-first jetpack-compose matryoshka openai-api embeddinggemma embeddings-api
-
Updated
May 24, 2026 - Kotlin
Tower Defense game where you shoot Russian nesting dolls.
-
Updated
Apr 21, 2022 - C
Small LLMs (135M to 1.7B) turned into embedding models that store each document in 16 bytes. Bidirectional attention, distilled from Qwen3 Embedding 8B and ColBERT, Matryoshka and binary aware training. Runs on Colab T4 and RunPod, ships to Sentence Transformers, vLLM, ONNX and the browser.
nlp retrieval transformers pytorch embeddings colab quantization webgpu distillation onnx faiss rag huggingface matryoshka colbert llm runpod vectorsearch vllm mteb
-
Updated
Oct 26, 2026 - Python
voyage-4-nano text embeddings on Apple silicon via MLX
-
Updated
Aug 4, 2026 - Python
Add this topic to your repo
To associate your repository with the matryoshka topic, visit your repo's landing page and select "manage topics."