Search results

v3 training data

Status: Open.

#203 In TIGER-AI-Lab/VLM2Vec;

· jaycheng6076 opened on May 17, 2026

Add jina omni v5 embedding models to MMEB-V2

Status: Open.

#202 In TIGER-AI-Lab/VLM2Vec;

· cktang88 opened on May 13, 2026

评估支持使用vllm框架部署的模型吗

Status: Open.

#200 In TIGER-AI-Lab/VLM2Vec;

· sanshi9523 opened on Apr 3, 2026

VD-Vidore-V2 evaluation metrics do not match the paper.

Status: Open.

#194 In TIGER-AI-Lab/VLM2Vec;

· Lebron-James777 opened on Mar 11, 2026

How to support eval Qwen2.5/3-omni

Status: Open.

#193 In TIGER-AI-Lab/VLM2Vec;

· jianghuyihei opened on Mar 5, 2026

one gpu oom

Status: Open.

#192 In TIGER-AI-Lab/VLM2Vec;

· FightingFighting opened on Feb 11, 2026

Does this code support training baseline models (GME, LamRA) on private datasets?

Status: Open.

#191 In TIGER-AI-Lab/VLM2Vec;

· xxzhang99 opened on Jan 19, 2026

how to eval a openapi model

Status: Open.

#189 In TIGER-AI-Lab/VLM2Vec;

· simplew2011 opened on Jan 16, 2026

esg_reports_human_labeled_v2: discrepancy between test corpus size and the number of uploaded images

Status: Open.

#188 In TIGER-AI-Lab/VLM2Vec;

· sahel-sh opened on Jan 16, 2026

why not directly use the original Qwen implementation on huggingface?

RepliedThe author team has replied to the issue and will wait for any further discussion before closing it.The author team has replied to the issue and will wait for any further discussion before closing it.

Status: Open.

#183 In TIGER-AI-Lab/VLM2Vec;

· FightingFighting opened on Dec 20, 2025

Backward is missing in the training_step method of the GradCacheLateProcessTrainer

Status: Open.

#181 In TIGER-AI-Lab/VLM2Vec;

· kalik-murbanov opened on Dec 10, 2025

Question on CLIP finetuning in VLM2Vec-v1

Status: Open.

#178 In TIGER-AI-Lab/VLM2Vec;

· jaeseokbyun opened on Nov 26, 2025