Who developed VLM2Vec LoRA and how large is it?

VLM2Vec LoRA is developed by TIGER-Lab. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate VLM2Vec LoRA?

VLM2Vec LoRA is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

VLM2Vec LoRA by TIGER-Lab

Name: VLM2Vec LoRA
Author: TIGER-Lab

VLM2Vec LoRA is an open-source language model by TIGER-Lab. Features: LLM, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.15.

Arxiv:2410.05160 Base model:finetune:microsoft/... Base model:microsoft/phi-3.5-v... Conversational Custom code Dataset:tiger-lab/mmeb-train Embedding En Instruct Lora Phi3 v Region:us Vision

Model Card on HF 🤗: https://huggingface.co/TIGER-Lab/VLM2Vec-LoRA

VLM2Vec LoRA 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 Name	VLM2Vec LoRA
Repository 🤗	https://huggingface.co/TIGER-Lab/VLM2Vec-LoRA
Base Model(s)	microsoft/Phi-3.5-vision-instruct microsoft/Phi-3.5-vision-instruct
Required VRAM	0 GB
Updated	2026-07-28
Maintainer	TIGER-Lab
Instruction-Based	Yes
Model Files	0.0 GB 0.0 GB
Supported Languages	en
Model Architecture	AutoModelForCausalLM
License	apache-2.0
Model Max Length	131072
Is Biased	none
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	k_proj\|out_proj\|gate_up_proj\|down_proj\|v_proj\|qkv_proj\|o_proj\|q_proj
LoRA Alpha	64
LoRA Dropout	0.1
R Param	8

Rank the VLM2Vec LoRA capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to VLM2Vec LoRA

Best Alternatives	Context / RAM	Downloads	Likes
... Mini 4K Instruct Chinese Lora	0K / 0 GB	8	6
Falcon Camel Math Instruct	0K / 0 GB	2	1
Instruct Igel 001	0K / 12.9 GB	13	47
...emo Instruct 2407 EXL2 8bpw H8	0K / 12.6 GB	7	7
Dre Phi	0K / 7.6 GB	7	0
Phi 3 Mini 4K CodeInstruct	0K / 7.6 GB	10	0
...3 Mini 4K Instruct Text To Sql	0K / 7.6 GB	12	0
Phi 3 Mini 4K Python	0K / 7.6 GB	632	1
Pipi	0K / 2.4 GB	13	0

Note: green Score (e.g. "73.2") means that the model is better than TIGER-Lab/VLM2Vec-LoRA.