# Multimodal Dialogue

VoRA is a vision-language model based on 7B parameters, focusing on image-text-to-text conversion tasks.

VoRA is a vision-language model based on 7B parameters, capable of processing image and text inputs to generate text outputs.

This is the GGUF quantized version of the Qwen2.5-VL-7B-Instruct model, suitable for multimodal tasks and supports both image and text inputs.

Q-SiT Mini is a lightweight image quality assessment and dialogue model, focusing on image quality analysis and scoring.

LLaVA-NeXT-Video-7B-hf is a video-based multimodal model capable of processing video and text inputs to generate text outputs.

InternVL2_5-4B-AWQ is the AWQ quantized version of InternVL2_5-4B using autoawq, supporting multilingual and multimodal tasks.

A video multimodal large language model enhanced by Long and Rich Context (LRC) modeling, improving existing MLLMs by enhancing the perception of fine-grained details and capturing long-term temporal structures

InternLM-XComposer2.5-Chat is a dialogue model trained based on InternLM-XComposer2.5-7B, showing significant improvements in multimodal instruction following and open-ended dialogue capabilities.

This is the GPTQ quantized 8-bit version of the QVQ-72B-Preview-abliterated model, supporting image-text-to-text conversion tasks.

Apollo is a series of large multimodal models focused on video understanding, excelling in processing up to one-hour-long video content, supporting complex video QA and multi-turn dialogues.

Apollo is a series of large multimodal models focused on video understanding, excelling in tasks such as long video content comprehension, temporal reasoning, and complex video question answering.

Mini-InternVL2-DA-RS is a multimodal model optimized for the remote sensing image domain, based on the Mini-InternVL architecture. It has been fine-tuned through a domain adaptation framework and demonstrates excellent performance in remote sensing image understanding tasks.

VARCO-VISION-14B is a powerful English-Korean visual language model that supports image and text input to generate text output, equipped with localization, referencing, and OCR capabilities.

A BitsAndBytes NF4 quantized version based on Aria-sequential_mlp, suitable for image-to-text tasks with approximately 15.5 GB VRAM requirement.

mPLUG-Owl3 is an advanced multimodal large language model focused on addressing the challenges of long image sequence understanding, significantly improving processing speed and sequence length through the Hyper Attention mechanism.

mPLUG-Owl3 is an advanced multimodal large language model focused on addressing the challenges of long image sequence understanding, significantly improving processing speed and sequence length through the Hyper Attention mechanism.

VideoChat2-HD-hf is a multimodal video understanding model based on Mistral-7B, focusing on video-to-text conversion tasks.

This is the 4-bit quantized version of Qwen2-Audio-7B-Instruct, developed based on Alibaba Cloud's original Qwen model. It is an audio-text multimodal large language model.

InternVideo2-Chat-8B-InternLM2.5 is a video-text multimodal model that enhances video understanding and human-computer interaction by integrating the InternVideo2 video encoder with a large language model (LLM).

mPLUG-Owl3 is a cutting-edge multimodal large language model designed to tackle the challenges of long image sequence understanding, supporting single-image, multi-image, and video tasks.

AI virtual anchor BanBan model, a virtual anchor assistant designed specifically for the NTNU VLSI club, capable of image-text-to-text conversion.

LLaVA-Saiga-8b is a vision-language model (VLM) developed based on the IlyaGusev/saiga_llama3_8b model, primarily optimized for Russian tasks while retaining English processing capabilities.

A lightweight visual question answering model based on TinyLlama-1.1B, trained using the BakLlava codebase, supporting image content understanding and question-answering tasks.

llava-calm2-siglip is an experimental vision-language model capable of answering questions about images in Japanese and English.

A multimodal dialogue model fine-tuned based on google/paligemma-3b-mix-448, optimized for multi-turn conversation scenarios

The int4 quantized version of MiniCPM-Llama3-V 2.5, significantly reducing GPU VRAM usage (approximately 9GB)

CogVLM2 is a multimodal dialogue model based on Meta-Llama-3-8B-Instruct, supporting both Chinese and English, with 8K context length and 1344*1344 resolution image processing capabilities.

The int4 quantized version of MiniCPM-Llama3-V 2.5 significantly reduces GPU VRAM usage to approximately 9GB, suitable for visual question answering tasks.

360VL is an open-source large multimodal model developed based on the LLama3 language model, featuring powerful image understanding and bilingual text support capabilities.

CogVLM2 is a multimodal large model built on Meta-Llama-3-8B-Instruct, supporting both Chinese and English with powerful image understanding and dialogue capabilities.

CogVLM2 is a multimodal large model built upon Meta-Llama-3-8B-Instruct, supporting image understanding and dialogue tasks with 8K context length and 1344x1344 image resolution processing capability.

360VL is a multimodal model developed based on the LLama3 language model, featuring powerful image understanding and bilingual dialogue capabilities.

A multimodal dialogue model developed through instruction fine-tuning based on Libra-Base, capable of image understanding and text generation

A large multimodal model trained based on the LLaVA-v1.5 framework, using the 8-billion-parameter Meta-Llama-3-8B-Instruct as the language backbone and equipped with a CLIP-based visual encoder.

LLaVA model fine-tuned based on Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336, supporting image-to-text tasks

A multimodal model fine-tuned based on Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336, supporting image understanding and text generation

A LLaVA model fine-tuned based on Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336, supporting image-text-to-text tasks

LLaVA-Phi-3-mini is a fine-tuned LLaVA model based on Phi-3-mini-4k-instruct and CLIP-ViT-Large-patch14-336, specializing in image-to-text tasks.

LLaVA model fine-tuned based on Phi-3-mini-4k-instruct and CLIP-ViT-Large-patch14-336, supporting image-to-text tasks

This model is a GGUF format conversion based on xtuner/llava-llama-3-8b-v1_1, supporting multimodal processing of images and text.