Qwen/Qwen2.5-VL-7B-Instruct

Qwen2.57Binit

#69 opened 12 days ago by

miaohuairui

科研需求

#68 opened 13 days ago by

zjutEvan

Add ScreenSpot-Pro evaluation result (Qwen2.5-VL-7B-Instruct)

#67 opened 19 days ago by

merve

Add missing Apache-2.0 license (aligned with other Qwen model repos)

#66 opened about 1 month ago by

angel-al

Report Model not working via Hugging Face Router (50001 Internal Error)

1

#65 opened 3 months ago by

Mustafahmdan

The model suddenly is not working

5

#64 opened 3 months ago by

Mustafahmdan

Token Count Calculation in SFT Data Distribution Curation

#63 opened 5 months ago by

tcy006

Transformers Version Error

#62 opened 5 months ago by

thyjeff

Optimal image format and size

#60 opened 6 months ago by

yiftachd

weien2

#59 opened 7 months ago by

weien2538

Why tie_word_embeddings is False for 7B model?

#58 opened 8 months ago by

pengzhenghao97

Update README.md

#56 opened 9 months ago by

stevezkw

Fix Video Inference - TypeError: process_vision_info() got an unexpected keyword argument 'return_video_kwargs'

#55 opened 9 months ago by

developer0hye

Batch inference gives addCriterion

2

#54 opened 9 months ago by

clyao-123

Output logits differ significantly for differenet attn_implementations on image inputs

👍 2

1

#53 opened 9 months ago by

zzigakovacic

Confusion with the parameter fixed in visual ViT merger in source code.

#52 opened 10 months ago by

Bytes-Lin

Update README.md

#51 opened 10 months ago by

xiaowei4ai

In-context learning

#50 opened 10 months ago by

Gilad-Deutch

"ValueError: Image features and image tokens do not match: tokens: 0, features 2852"

1

#49 opened 10 months ago by

jdkruzr

Context Length

#48 opened 11 months ago by

Fujiao

run error

#47 opened 11 months ago by

yangtao1

Model cannot be downloaded

👍 18

3

#46 opened 11 months ago by

sadabshiper

support function calling?

#44 opened 11 months ago by

tasia

Video Inference --> RuntimeError: torch.cat(): expected a non-empty list of Tensors

#43 opened 11 months ago by

caput

Inference on Tesla P402 or RTX 2080Ti 2, after fixing a bug(?)

#42 opened 12 months ago by

luweigen

Update README.md

#40 opened 12 months ago by

megladagon

Chat template does not work

😔 6

#39 opened about 1 year ago by

tonydavis629

Poor performance with simple table extraction task

3

#38 opened about 1 year ago by

hanshupe

Base model for Qwen2.5-VL-7B-Instruct

1

#37 opened about 1 year ago by

zzlynxSG

Request: DOI

1

#36 opened about 1 year ago by

mojan3

pixel_values to RGB image

#33 opened about 1 year ago by

ococq

Update README.md

1

#32 opened about 1 year ago by

teowu

Qwen2.5-VL-7B-Instruct License?

1

#31 opened about 1 year ago by

radames

Add link to paper page

#30 opened about 1 year ago by

nielsr

For now, use this version of Transformers for vLLM.

3

#29 opened about 1 year ago by

mkvn

Fine-tuning for Image Captioning and Image QA with Segmented Images

👍 1

#28 opened about 1 year ago by

badhon1512

Model architectures ['Qwen2_5_VLForConditionalGeneration'] are not supported for now.

#27 opened about 1 year ago by

liujh123

No module named 'transformers.models.qwen2_5_vl.image_processing_qwen2_5_vl'

1

#26 opened about 1 year ago by

risonlovesakura

XXX

#25 opened about 1 year ago by

mpasternak

finetune

🔥👍 12

#23 opened about 1 year ago by

andrewdeeplearning

[Error] (Qwen2.5-VL-instruct-7B) Qwen2TokenizerFast object has no attribute 'tokenizer'

4

#21 opened about 1 year ago by

yus002

Vision tokens missing from chat template

#20 opened about 1 year ago by

depasquale

Batch Inference会报错

4

#19 opened about 1 year ago by

dingguofeng

Hardware and vram requiremnt to run this model?

9

#18 opened about 1 year ago by

IronmanSnap

Request: DOI

#16 opened about 1 year ago by

arashinokage

Can we use tools with this model?

👍 1

#15 opened about 1 year ago by

barleyspectacular

Bounding boxes coordinates

6

#13 opened about 1 year ago by

ljoana

What engine can I use to deploy this model?

🔥➕ 10

3

#12 opened about 1 year ago by

jjovalle99

Finetuning scripts for Qwen2.5-VL (No llama-factory)

👍 16

#11 opened about 1 year ago by

2U1

Merging "Qwen2.5-7B-Instruct" text adapter into "Qwen2.5-VL-7B-Instruct" model

1

#9 opened about 1 year ago by

rameshch

Qwen2.57Binit

科研需求

Add ScreenSpot-Pro evaluation result (Qwen2.5-VL-7B-Instruct)

Add missing Apache-2.0 license (aligned with other Qwen model repos)

Report Model not working via Hugging Face Router (50001 Internal Error)

The model suddenly is not working

Token Count Calculation in SFT Data Distribution Curation

Transformers Version Error

Optimal image format and size

weien2

Why tie_word_embeddings is False for 7B model?

Update README.md

Fix Video Inference - TypeError: process_vision_info() got an unexpected keyword argument 'return_video_kwargs'

Batch inference gives addCriterion

Output logits differ significantly for differenet attn_implementations on image inputs

Confusion with the parameter fixed in visual ViT merger in source code.

Update README.md

In-context learning

"ValueError: Image features and image tokens do not match: tokens: 0, features 2852"

Context Length

run error

Model cannot be downloaded

support function calling?

Video Inference --> RuntimeError: torch.cat(): expected a non-empty list of Tensors

Inference on Tesla P40*2 or RTX 2080Ti *2, after fixing a bug(?)

Update README.md

Chat template does not work

Poor performance with simple table extraction task

Base model for Qwen2.5-VL-7B-Instruct

Request: DOI

pixel_values to RGB image

Update README.md

Qwen2.5-VL-7B-Instruct License?

Add link to paper page

For now, use this version of Transformers for vLLM.

Fine-tuning for Image Captioning and Image QA with Segmented Images

Model architectures ['Qwen2_5_VLForConditionalGeneration'] are not supported for now.

No module named 'transformers.models.qwen2_5_vl.image_processing_qwen2_5_vl'

XXX

finetune

[Error] (Qwen2.5-VL-instruct-7B) Qwen2TokenizerFast object has no attribute 'tokenizer'

Vision tokens missing from chat template

Batch Inference会报错

Hardware and vram requiremnt to run this model?

Request: DOI

Can we use tools with this model?

Bounding boxes coordinates

What engine can I use to deploy this model?

Finetuning scripts for Qwen2.5-VL (No llama-factory)

Merging "Qwen2.5-7B-Instruct" text adapter into "Qwen2.5-VL-7B-Instruct" model

Inference on Tesla P402 or RTX 2080Ti 2, after fixing a bug(?)