Alibaba-NLP
/

gme-Qwen2-VL-2B-Instruct

Sentence Similarity

sentence-transformers

image-text-to-text

Eval Results (legacy)

Model card Files Files and versions

Resources

View closed (11)

Training strategy

#26 opened 8 days ago by

Do you have any plans to update the embedding model using Qwen3-VL as the base model ?

#25 opened 5 months ago by

How to calculate video embedding?

#24 opened 8 months ago by

modelscope和huggingface下载的config文件不一样

#23 opened 10 months ago by

andrewdeeplearning

About fine-tuned

#22 opened 10 months ago by

How to enable bidirectional attention?

#21 opened 11 months ago by

finetuning

#20 opened 11 months ago by

error with AutoModel GmeQwen2VLConfig after upgrade

#16 opened 12 months ago by

Does batch_size=128 during training refer to the global or single-GPU batch size, and is it trained using DeepSpeed Zero3?

#13 opened about 1 year ago by

training code supported

#8 opened about 1 year ago by

Results on M-BEIR

#7 opened about 1 year ago by

LoRA weights

#6 opened over 1 year ago by

Fused-Modal Data

#5 opened over 1 year ago by

training batch size

#3 opened over 1 year ago by

Training code release

#2 opened over 1 year ago by