# Instruction Following

A 9B-parameter chat model based on GLM-4 architecture, supporting Chinese and English dialogues, quantized for various hardware environments

Shisa V2 is a bilingual (Japanese/English) general-purpose chat model series trained by Shisa.AI, optimized based on Llama-3.3-70B-Instruct, focusing on improving Japanese task performance while maintaining English capabilities.

A creative writing model based on fine-tuned merges of Gemma 3 12B IT and PT, optimized for role-playing with improved character differentiation and reduced identity confusion.

An 8B-parameter language model based on the Llama 3.1 architecture, created by merging multiple models with mergekit, capable of text generation

GLM-Edge-1.5B-Chat is a 1.5 billion parameter-scale chat model based on the GLM architecture, suitable for Chinese dialogue scenarios.

LLaVA-NeXT-Video is an open-source multimodal chatbot optimized through mixed training on video and image data, possessing excellent video understanding capabilities.

LLaVA-NeXT-Video is an open-source multimodal chatbot that achieves excellent video understanding capabilities through mixed training on video and image data, reaching SOTA level among open-source models on the VideoMME benchmark.

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.

A multimodal model integrating Meta-Llama-3-8B-Instruct and LLaVA-v1.5, providing advanced vision-language understanding capabilities

LLaVA-Next-Video is an open-source multimodal dialogue model, fine-tuned with multimodal instruction-following data on large language models, supporting video and text multimodal interactions.

LLaVA-Next-Video is an open-source multimodal dialogue robot, fine-tuned from a large language model, supporting multimodal interaction with video and text.

LLaVA-Gemma-7b is a large multimodal model trained based on the LLaVA-v1.5 framework, using google/gemma-7b-it as the language backbone combined with a CLIP visual encoder, suitable for multimodal understanding and generation tasks.

LLaVA-Gemma-2b is a large multimodal model trained based on the LLaVA-v1.5 framework, utilizing the 2-billion-parameter Gemma-2b-it as the language backbone combined with a CLIP visual encoder.

LLaVA is an open-source multimodal chatbot based on the Transformer architecture, offering various model versions that balance size and quality through quantization techniques.

LLaVA is an open-source multimodal chatbot trained by fine-tuning LLM on multimodal instruction-following data. This version is the GGUF quantized version, offering multiple quantization options.

LLaVA is an open-source multimodal chatbot, fine-tuned on LLaMA/Vicuna and trained with GPT-generated multimodal instruction-following data.

LLaVA is an open-source multimodal chatbot, trained by fine-tuning LLM on multimodal instruction-following data. This version is the GGUF quantized version, offering multiple quantization options.

LLaVA is an open-source multimodal chatbot, fine-tuned on large language models with multimodal instruction-following data.

LLaVA is an open-source multimodal chatbot, trained by fine-tuning large language models on multimodal instruction-following data.

Openchat 3.5 0106 is an open-source dialogue model based on the Mistral architecture, developed by the OpenChat team. This model focuses on delivering high-quality conversational experiences and supports various dialogue tasks.

LLaVA is an open-source multimodal chatbot, based on the LLaMA/Vicuna architecture, fine-tuned with multimodal instruction-following data.

Experimental stitched model, created by merging Thorn-13B and Norn Maid-13B, excels in role-playing scenarios

OpenChat 3.5 7B is a 7B-parameter large language model based on the Mistral architecture, developed by the OpenChat team and released under the Apache 2.0 license.

LLaVA is an open-source multimodal chatbot, fine-tuned from LLaMA/Vicuna and trained on GPT-generated multimodal instruction-following data.

LLaVA is an open-source multimodal chatbot, fine-tuned on GPT-generated multimodal instruction data based on the LLaMA/Vicuna model.

LLaVA is an open-source multimodal chatbot, fine-tuned on GPT-generated multimodal instruction-following data based on LLaMA/Vicuna.

LongLoRA is an efficient fine-tuning technique for large language models with long context processing capabilities, achieving this through shifted short attention mechanisms, supporting context lengths from 8k to 100k.

LLaVA is an open-source multimodal chatbot, fine-tuned based on LLaMA/Vicuna and integrated with visual capabilities, supporting interactions with both images and text.

The first open-source large language model with instruction-following capability for explainable mental health analysis

The first open-source large language model with instruction-following capability for explainable mental health analysis, fine-tuned based on LLaMA2-chat-7B

SynthIA (Synthetic Intelligence Agent) is an LLama-2-70B model trained on an Orca-style dataset, excelling in instruction following and long dialogues.

Mythalion 13B is a 13B-parameter large language model developed by PygmalionAI, based on the Llama architecture, specializing in text generation and instruction-following tasks.