Ignasi

moondream2 is a small vision language model designed to run efficiently on edge devices.

Llama 3.1 is a new state-of-the-art model from Meta available in 8B, 70B and 405B parameter sizes.

The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases,

Embedding models on very large sentence level datasets

Phi-3 is a family of lightweight 3B (Mini) and 14B (Medium) state-of-the-art open models by Microsof

Qwen2 is a new series of large language models from Alibaba group

Qwen2.5 models are pretrained on Alibaba latest large-scale dataset, encompassing up to 18 trillion

A high-performing open embedding model with a large token context window

A state-of-the-art fact-checking model developed by Bespoke Labs.

Meta's Llama 3.2 goes small with 1B and 3B models

Llama 3.1 is a new state-of-the-art model from Meta

CodeGemma is a collection of powerful, lightweight models that can perform a variety of coding tasks

A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function ca

StarCoder2 is the next generation of transparently trained open code LLMs that comes in three sizes:

LLaVA is a novel end-to-end trained large multimodal model that combines a vision encoder and Vicuna

A SOTA fact-checking model developed by Bespoke Labs

A suite of text embedding models by Snowflake, optimized for performance

A family of small models with 135M, 360M, and 1.7B parameters, trained on a new high-quality dataset

The 7B model released by Mistral AI, updated to version 0.3

A series of models that convert HTML content to Markdown content, which is useful for content conver

A new small LLaVA model fine-tuned from Phi 3 Mini

A lightweight AI model with 3.8 billion parameters with performance overtaking similarly and larger

BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Ling

Google Gemma 2 is a high-performing and efficient model available in three sizes: 2B, 9B, and 27B

DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens

The latest series of Code-Specific Qwen models, with significant improvements in code generation, co

State-of-the-art large embedding model from mixedbread.ai

A 3.8B model fine-tuned on a private high-quality synthetic dataset for information extraction, base