Hugging Face's logo

Qwen
/
Qwen2-VL-7B-Instruct

Image-Text-to-Text
Transformers
Safetensors
English
qwen2_vl
multimodal
conversational
Inference Endpoints
Model card Files Community
47
New discussion

How many tokens is one image?

1
#47 opened 15 days ago by MoritzLaurer

RuntimeError: CUDA error: operation not permitted when stream is capturing

1
#46 opened 15 days ago by yuyanggo

Adding Evaluation Results
#45 opened 15 days ago by leaderboard-pr-bot

CUDA error: CUBLAS_STATUS_EXECUTION_FAILED
#44 opened 15 days ago by yuyanggo

KeyError: 'qwen2_vl' loading from Transformers

1
#42 opened 23 days ago by KevalRx

Batch inference on many images

1
#41 opened 25 days ago by yadavsaakash

Handling multiple images in a pdf to preserve context during processing.

1
#40 opened 25 days ago by ananthv

Questions about Naive Dynamic Resolution and the vision mask

1
#39 opened 29 days ago by YaYaGeGe

it run on cpu
#38 opened about 1 month ago by sdyy

Request for Help: Passing an Image in cURL with vLLM

2
#36 opened about 2 months ago by ananthv

Ollama api setup for Qwen2

3
#35 opened about 2 months ago by RagulMahendran

Neto discussion
#34 opened about 2 months ago by Neto1780

An error occurred: shape mismatch

4
#33 opened about 2 months ago by VeeP

Finetuning script using HuggingFace (No llama-factory)

10
#32 opened about 2 months ago by 2U1

Able to successfully deploy as Inference Endpoint?
#31 opened about 2 months ago by philglazer

GGUF models

1
#30 opened about 2 months ago by mariahelenass

可以用来做多模态检索吗
#29 opened about 2 months ago by Lecheal

OCR on image

2
#28 opened about 2 months ago by glitchyordis

Update chat_template.json to incorporate `generation` tag

1
#27 opened about 2 months ago by linyueqian

Request: DOI
#26 opened about 2 months ago by samzong

Value of fps for video inference

3
#25 opened about 2 months ago by shivanis14

Are GGUF models available?
#24 opened about 2 months ago by smcleod

support in ollama

1
#21 opened about 2 months ago by Goekdeniz-Guelmez

when i use torch.float16，i face this problem probability tensor contains either `inf`, `nan` or element < 0

2
#20 opened 2 months ago by als-991011

Can it be run on a 3090 with 24gb VRAM?

2
#18 opened 2 months ago by mnemic

Nerfed with people

2
#17 opened 2 months ago by spawn99

ValueError: Unrecognized configuration class <class 'transformers.models.qwen2_vl.configuration_qwen2_vl.Qwen2VLConfig'> for this kind of AutoModel: AutoModelForSeq2SeqLM.

1
#16 opened 2 months ago by vinz1396

Arabic
#15 opened 2 months ago by MubashshirMohammad

When extracting text from an image, some text is missing.
#14 opened 2 months ago by wol2001

Support for multi-round question answering in Qwen2-VL-7B-Instruct
#12 opened 2 months ago by zhanchao019

Working sample for mac

13
#11 opened 2 months ago by spawn99

RuntimeError: MPS backend out of memory.

1
#8 opened 2 months ago by TahaZk

LoRA Finetuning Tool for Qwen2-VL-7B in Web UI (DPO updated)

12
#2 opened 2 months ago by hiyouga

🍭 Fine-tuning support for Qwen2-VL-7B-Instruct

5
#1 opened 2 months ago by study-hjt