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

VLM2Vec Full by TIGER-Lab

 »  All LLMs  »  TIGER-Lab  »  VLM2Vec Full   URL Share it on

  31879   
  Arxiv:2410.05160   Autotrain compatible Base model:finetune:microsoft/... Base model:microsoft/phi-3.5-v...   Conversational   Custom code   Dataset:tiger-lab/mmeb-train   Embedding   En   Instruct   Phi3 v   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Vision
Model Card on HF 🤗: https://huggingface.co/TIGER-Lab/VLM2Vec-Full 

VLM2Vec Full Benchmarks

LLME Score: 0.29884
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
VLM2Vec Full (TIGER-Lab/VLM2Vec-Full)

VLM2Vec Full Parameters and Internals

Model Type 
multimodal embedding
Additional Notes 
The model uses an [EOS] token as the representation of the multimodal inputs.
Supported Languages 
en (English)
Training Details 
Data Sources:
TIGER-Lab/MMEB-train
Methodology:
Converting an existing well-trained VLM into an embedding model with contrastive learning.
LLM NameVLM2Vec Full
Repository 🤗https://huggingface.co/TIGER-Lab/VLM2Vec-Full 
Base Model(s)  microsoft/Phi-3.5-vision-instruct   microsoft/Phi-3.5-vision-instruct
Model Size4.1b
Required VRAM8.3 GB
Updated2025-02-22
MaintainerTIGER-Lab
Model Typephi3_v
Instruction-BasedYes
Model Files  4.9 GB: 1-of-2   3.4 GB: 2-of-2   4.9 GB: 1-of-2   3.4 GB: 2-of-2
Supported Languagesen
Model ArchitecturePhi3VForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.46.1
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to VLM2Vec Full

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Vision Instruct128K / 8.3 GB296679664
Phi 3 Vision 128K Instruct128K / 8.3 GB142395950
Phi 3.5 Vision Instruct Bf16128K / 8.3 GB1002
...hi 3 HornyVision 128K Instruct128K / 8.3 GB12427
...on 128K Instruct No Flash Attn128K / 8.3 GB130
Phi 3 Vision 128K Instruct128K / 8.3 GB140
Phi 3 Vision Win Snap128K / 8.3 GB301
Note: green Score (e.g. "73.2") means that the model is better than TIGER-Lab/VLM2Vec-Full.

Rank the VLM2Vec Full 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? 43470 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.
Release v20241227
  Support LLM Explorer