Gemma 3 4B IT GGUF is a lightweight open - source language model launched by Google DeepMind. It is built based on the same research and technology as the Gemini model. This model has a large context window of 128K, supports more than 140 languages, and uses the GGUF format for easy deployment and operation on various devices.

Natural Language ProcessingGgufEnglish

Gemma 3 1B IT GGUF is the GGUF format version of the lightweight open-source language model developed by Google DeepMind. This model is converted from the Gemma 3 1B IT (instruction fine-tuning) model, with a large context window of 128K, supporting over 140 languages, and is suitable for deployment in resource-constrained environments.

Natural Language ProcessingGgufEnglish

GemMoE is a Mixture of Experts (MoE) model based on Deepmind's Gemma architecture, integrating 8 individually fine-tuned Gemma models, with 2 experts per token. It is powerful and easy to train and infer.

Natural Language ProcessingTransformers

IDEFICS is an open-source reproduction of DeepMind's proprietary visual language model Flamingo, supporting multimodal input (image + text) and generating text output.

MultimodalTransformersEnglish

IDEFICS is an open-source reproduction of DeepMind's proprietary visual language model Flamingo. It is a multimodal model that can accept arbitrary sequences of images and text as input and generate text output.

MultimodalTransformersEnglish

IDEFICS is an open-source multimodal model capable of processing both image and text inputs to generate text outputs, serving as an open-source reproduction of Deepmind's Flamingo model.

MultimodalTransformersEnglish

IDEFICS-9B is a 9-billion-parameter multimodal model capable of processing both image and text inputs to generate text outputs. It is an open-source replication of Deepmind's Flamingo model.

MultimodalTransformersEnglish

Perceiver IO is a general-purpose Transformer architecture capable of processing multiple modalities. This model is specifically designed for image classification tasks and pretrained on the ImageNet dataset.

Computer VisionTransformers

This model is a financial text sentiment classification model fine-tuned on the financial_phrasebank dataset based on deepmind/language-perceiver.

Natural Language ProcessingTransformers

A general-purpose vision perceiver model pre-trained on ImageNet, utilizing convolutional preprocessing and Transformer architecture, supporting image classification tasks

Computer VisionTransformers

Pre-trained on BERT-style masked language modeling tasks, supports multimodal Transformer model processing UTF-8 byte inputs

Natural Language ProcessingTransformersEnglish

A general-purpose vision perceiver model pre-trained on ImageNet, using learned position embeddings to process image inputs

Computer VisionTransformers