ml-ferret

End-to-end MLLM, enabling precise referencing and localization.

CommonProductProgrammingMachine LearningLanguage Model

ml-ferret is an end-to-end machine learning language model (MLLM) that can accept various forms of references and respond with precise localization in multimodal environments. It combines mixed regional representations and spatially aware visual samplers, supporting fine-grained and open-vocabulary referencing and localization. Additionally, ml-ferret includes the GRIT dataset (approximately 1.1 million samples) and the Ferret-Bench evaluation benchmark.

Best AI Websites & Tools

ml-ferret

ml-ferret Visit Over Time

ml-ferret Visit Trend

ml-ferret Visit Geography

ml-ferret Traffic Sources

ml-ferret Alternatives

MedTrinity-25M — A large-scale multimodal medical dataset

Spirit LM — Multimodal language model that integrates text and speech

Zamba2-7B — High-performance small language model

UniMuMo — Unified model for text, music, and motion generation.

AMD-Llama-135m — A high-performance language model trained by AMD

Molmo — Advanced Multimodal AI Model Family

Pixtral 12B — The first multimodal Mistral model, supporting hybrid task processing for images and text.

pixtral-12b-240910 — A multimodal large language model that supports understanding of both images and text.

ell — A lightweight programming library for language models, treating prompts as functions.

West Lake AI Model — A multimodal model with high emotional and intellectual intelligence

MiniCPM3-4B — High-performance third-generation MiniCPM series model.

Phi-3.5-vision — An advanced multimodal model that supports image and text understanding.

Data-Juicer — A one-stop data processing system that provides high-quality data for large language models.

MINT-1T — A multimodal dataset comprising one trillion tokens and 3.4 billion images.

DCLM-baseline — High-performance language model benchmark dataset

UltraEdit — Large-Scale Image Editing Dataset

Multi-Token Prediction — A multi-token prediction model designed to boost the efficiency and performance of language models

VideoLLaMA2-7B — A large video-language model that provides video question answering and video captioning.

Samba — Official implementation of an efficient infinite context language model

FlashRAG — Efficient Toolkit for Retrieval-Augmented Generation Research

Gemini 1.5 Flash — A lightweight and high-performance AI model from Google, designed for large-scale, high-frequency tasks.

MAP-NEO — MAP-NEO is an entirely open-source large language model offering advanced natural language processing capabilities.

Prometheus-Eval — An open-source toolkit for evaluating other language models

LLaVA++ — LLaVA++ extends the LLaVA model by integrating Phi-3 and LLaMA-3, enhancing the interaction capability between visual and language models.

OpenELM — OpenELM is a family of efficient language models equipped with an open-source training and inference framework.

MNBVC — MNBVC is a massive Chinese corpus comparable to the 40T data used to train ChatGPT.

Qwen-VL — General-purpose Visual Language Model

imp-v1-3b — A powerful multimodal small language model.

SpeechGPT — Multimodal Language Model