LLM EXPLORER 59,420 MODELS INDEXED

LLaVA NeXT Video 7B DPO by lmms-lab

By lmms-lab · 254 downloads
HF Repo ↗ Copy URL

LLaVA NeXT Video 7B DPO is an open-source language model by lmms-lab. Features: 7b LLM, VRAM: 14.2GB, Context: 4K, License: llama2, LLM Explorer Score: 0.12.

  Llava   Region:us   Safetensors   Sharded   Tensorflow   Video-text-to-text
Model Card on HF 🤗: https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-7B-DPO 

LLaVA NeXT Video 7B DPO Parameters and Internals

Model Type 
video-text-to-text, multimodal, chatbot
Use Cases 
Areas:
research
Primary Use Cases:
research on large multimodal models and chatbots
Training Details 
Data Sources:
LAION/CC/SBU, BLIP, GPT, VQA, ShareGPT, VideoChatGPT-Instruct, ShareGPTVideo
Methodology:
Fine-tuning LLM on multimodal instruction-following data
Training Time:
April 2024
LLM NameLLaVA NeXT Video 7B DPO
Repository 🤗https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-7B-DPO 
Model Size7b
Required VRAM14.2 GB
Updated2026-08-03
Maintainerlmms-lab
Model Typellava
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.3 GB: 3-of-3   0.0 GB
Model ArchitectureLlavaLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.39.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to LLaVA NeXT Video 7B DPO

Best Alternatives
Context / RAM
Downloads
Likes
Llava Merged Finetuned 7b32K / 15.1 GB11
Llava V1.6 Mistral 7B PATCHED32K / 15.1 GB178
KoLLaVA V1.5 Synatra 7B32K / 15.1 GB138
Llava V1.5 7B4K / 13.5 GB219094557
Llava V1.6 Vicuna 7B4K / 14.1 GB19939144
...va 1.5 Image Classification V34K / 23.3 GB2240
Vlm Rlaif Video Llava 7b4K / 14.2 GB60
Table Llava V1.5 7B4K / 14.2 GB913
Llava V1.5 7B M34K / 14.1 GB932
Som Llava V1.5 7B4K / 14.1 GB50
Note: green Score (e.g. "73.2") means that the model is better than lmms-lab/LLaVA-NeXT-Video-7B-DPO.