LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

LLaVA Video Llama 3 by weizhiwang

 »  All LLMs  »  weizhiwang  »  LLaVA Video Llama 3   URL Share it on

  139   

LLaVA Video Llama 3 is an open-source language model by weizhiwang. Features: 8b LLM, VRAM: 16.7GB, Context: 8K, License: cc, Instruction-Based, LLM Explorer Score: 0.14.

  Autotrain compatible Dataset:liuhaotian/llava-instr... Dataset:liuhaotian/llava-pretr...   En   Endpoints compatible   Instruct   Llava llama   Region:us   Safetensors   Sharded   Tensorflow   Video-text-to-text
Model Card on HF 🤗: https://huggingface.co/weizhiwang/LLaVA-Video-Llama-3 

LLaVA Video Llama 3 Benchmarks

LLME Score: 0.13701
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LLaVA Video Llama 3 (weizhiwang/LLaVA-Video-Llama-3)
🌟 Advertise your project 🚀

LLaVA Video Llama 3 Parameters and Internals

Model Type 
video-text-to-text, multimodal
Additional Notes 
Please refer to the GitHub repository for fine-tuning instructions and data preparation guidelines.
Training Details 
Data Sources:
liuhaotian/LLaVA-Instruct-150K, liuhaotian/LLaVA-Pretrain
Context Length:
8000
Model Architecture:
LLaVA architecture, visual encoder + MLP adapter + LLM backbone
Input Output 
Accepted Modalities:
video, text
Release Notes 
Version:
LLaVA-v1.6
Date:
5/14/2024
Notes:
Supports the latest LLama-3, phi-3, mistral-v0.1-7b models.
Version:
Video fine-tuning
Date:
6/4/2024
Notes:
The codebase supports video data fine-tuning for video understanding tasks.
LLM NameLLaVA Video Llama 3
Repository 🤗https://huggingface.co/weizhiwang/LLaVA-Video-Llama-3 
Model Size8b
Required VRAM16.7 GB
Updated2024-12-13
Maintainerweizhiwang
Model Typellava_llama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.8 GB: 4-of-4   0.0 GB
Supported Languagesen
Model ArchitectureLlavaLlamaForCausalLM
Licensecc
Context Length8192
Model Max Length8192
Transformers Version4.37.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_0|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to LLaVA Video Llama 3

Best Alternatives
Context / RAM
Downloads
Likes
Llama3 Llava Next 8B8K / 16.7 GB2548106
Llava Llama 3 8B MultiModal V18K / 16.1 GB31
...VA Meta Llama 3 8B Instruct FT8K / 16.7 GB612
LLaVA Meta Llama 3 8B Instruct8K / 16.7 GB112
LLaVA Llama 3 8B8K / 16.7 GB818
...Meta Llama 3 8B Instruct FT S28K / 16.7 GB34
Vip Llava Llama 3 8B8K / 16.8 GB60
Llava 1.5 Llama 3 8B8K / 16.7 GB50
Note: green Score (e.g. "73.2") means that the model is better than weizhiwang/LLaVA-Video-Llama-3.

Rank the LLaVA Video Llama 3 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52758 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer