# 7B Parameter Scale

Qwen2.5-VL-7B-Instruct is a multimodal model based on the Qwen2.5 architecture, supporting joint processing of images and text, suitable for vision-language tasks.

This model is a multimodal vision-language model converted from Qwen2.5-VL-7B-Instruct, supporting visual question answering tasks.

VideoChat-R1-thinking_7B is a multimodal model based on Qwen2.5-VL-7B-Instruct, focusing on video-text-to-text tasks.

A fine-tuned version based on the lmms-lab/llava-onevision-qwen2-7b-ov model, supporting video-text-to-text conversion tasks.

Qwen2-VL-7B-Instruct is a vision-language model based on the Qwen2 architecture, supporting multimodal input of images and text, suitable for various visual-language tasks.

olmOCR-7B-0225-preview is an image-to-text model based on OCR technology developed by AllenAI, designed to extract and recognize text content from images.

An instruction-following model fine-tuned based on unsloth/Qwen2-7B-Instruct, trained using Unsloth and TRL libraries with 2x speed improvement

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

This is a vision-language-action model fine-tuned using LoRA on the LIBERO-Object dataset, specifically designed for robotics.

Mistral-7B-Instruct-v0.3 is an instruction-tuned version of Mistral-7B, focusing on text generation tasks that follow human instructions.

Meta Chameleon is a hybrid-modality early-fusion foundational model developed by FAIR, supporting multimodal processing of images and text.

Zephyr 7B Gemma is a language model fine-tuned based on google/gemma-7b, trained on publicly available synthetic datasets using Direct Preference Optimization (DPO), designed to serve as a helpful assistant.

A large instruction-based language model customized for the legal domain, obtained through continued pretraining on Mistral-7B

RankZephyr is a language model trained based on Zephyr-7B-β, specializing in listwise reranking tasks and excelling across multiple datasets.

A Turkish medical domain large language model fine-tuned based on Mistral, supporting medical information Q&A in Turkish and English

This is a 7B-parameter harmless generation model designed for benchmarking RLHF (Reinforcement Learning from Human Feedback) poisoning attacks.

A Taiwanese LLM model based on LLaMa2-7b, further pre-trained on 20 billion Traditional Chinese tokens and fine-tuned with millions of dialogues

Mistral-7B-Instruct-v0.1 is a version of the Mistral-7B-v0.1 generative text model fine-tuned with various public dialogue datasets for instruction following.