Output in Markdown Format
#39 opened about 1 month ago
by
sarathrajendran552
![](https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/RmAQ1Gm-dHks1J1H5Qmtq.png)
Batch inference
#38 opened about 2 months ago
by
Stopwolf
![](https://cdn-avatars.huggingface.co/v1/production/uploads/64d9eca170891ac9b8d9fd38/hro6Ib5hFWWNBEu9J4XMe.png)
input_ids = torch.as_tensor(inputs.input_ids).cuda() 是否有问题?
#37 opened about 2 months ago
by
Moses25
Update modeling_GOT.py
#36 opened 2 months ago
by
lijicheng168
![](https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/NBWAlyzoNNDA7ifsjgFUz.png)
How can use GOT-OCR2_0 on vLLM or Ollama?
#35 opened 2 months ago
by
MhmdSyd
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/v81-ibO6ZY7wmQW7LDaHI.jpeg)
Allow to use PIL Image in chat function
1
#34 opened 2 months ago
by
akshayballal
RuntimeError: Current CUDA Device does not support bfloat16. Please switch dtype to float16.
2
#32 opened 3 months ago
by
taoyang2
This is a license-related question.
#31 opened 3 months ago
by
mkh0813
Different Results from the demo
#30 opened 3 months ago
by
Ryanchynoweth
![](https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/JbOxSPdq6T6QKJVCNAVR0.png)
transformers.js implementation
#29 opened 3 months ago
by
subjugate
support device type `cpu` generate
#26 opened 4 months ago
by
weege007
![](https://cdn-avatars.huggingface.co/v1/production/uploads/656dd9ef8a37acfa3f395392/MSwQwrSoUP9xy3tmcIrHa.jpeg)
MODEL NOT WORKING!!!!!!!
1
#25 opened 4 months ago
by
Pushpendra817
add stream params for chat and char_crop
#24 opened 4 months ago
by
weege007
![](https://cdn-avatars.huggingface.co/v1/production/uploads/656dd9ef8a37acfa3f395392/MSwQwrSoUP9xy3tmcIrHa.jpeg)
how to train it on custom dataset ?
#23 opened 4 months ago
by
Cherryblade29
support for onnx and openvino conversion
#22 opened 5 months ago
by
Jession01
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6126260dc64ee1aa6818807d/UaWlNPDk6jjOsJ709SaXQ.jpeg)
is it available to change output text format to Markdown?
10
#21 opened 5 months ago
by
MhmdSyd
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/v81-ibO6ZY7wmQW7LDaHI.jpeg)
How to this model for another languages
3
#20 opened 5 months ago
by
summon1d
Upload modeling_got.py
#18 opened 5 months ago
by
srimanth-d
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65d2fafb0cb9d915d37da24a/x8jCIe4yRceNN4b80dL_k.png)
Tesseract vs. GOT-OCR2_0: Which Performs Better for Text Extraction from Images?
2
#17 opened 5 months ago
by
bubbleMilkTea
cpu
3
#16 opened 5 months ago
by
goodasdgood
[output format] can the model's output be easily parsed? thx
2
#15 opened 5 months ago
by
Eric108
Device Support
1
#14 opened 5 months ago
by
YogeLiu
The results of the work are amazing,have some plans to support like llamacpp or other framework?
#13 opened 5 months ago
by
fsql
Alternative to filename string for image
1
#12 opened 5 months ago
by
codysmith
Inquiry Regarding Model Performance and Attention Mask
1
#11 opened 5 months ago
by
kartoshkafri
Bounding boxes in results
3
#9 opened 5 months ago
by
solankibhargav
![](https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/23HrDrHLEIoWwHHc7ZKWH.png)
Can it be used without GPU and CPU (intel or AMD) only?
4
#8 opened 5 months ago
by
jawad1347
Table extraction
3
#7 opened 5 months ago
by
Jkppp
megfile library error
2
#5 opened 5 months ago
by
don412
Support for CPU and MAC version
2
#4 opened 5 months ago
by
mallapraveen
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1650942368112-62676147dacab364889b7768.jpeg)
ModuleNotFoundError: No module named 'fcntl'
1
#3 opened 5 months ago
by
SK-1
T4 - bfloat 16 not support
10
#2 opened 5 months ago
by
SylvainV