How it is compared in bahchmarks with new model Paddle ocr 1.5 ?
#27 opened about 13 hours ago
by
dibu28
How do you calculate inference speed on OlmOCR-Bench?
π
1
1
#26 opened 1 day ago
by
Piperino
Throughput is slower than PadlleOCR-VL
1
#25 opened 3 days ago
by
TechNetiums
Regarding reasoning capability on image
#24 opened 3 days ago
by
Ajayan
The exact vocab size of the model
#22 opened 8 days ago
by
abdullahamlwakeb
Future suggestion about using available text layers
π
2
#21 opened 10 days ago
by
jondecker76
Prompt of Demo web
1
#20 opened 10 days ago
by
vanhdz2611
whats the best settings to run using vllm at very high concurrency
#19 opened 10 days ago
by
markwitt1
Fine-tuning for table bounding box extraction
1
#18 opened 11 days ago
by
TheOfficialAJ
Fine-tune for structured extraction
π
1
1
#17 opened 11 days ago
by
Glider95
x,y coordinates
1
#16 opened 12 days ago
by
Superdooperhero
Incredible Model, Thank You!
β€οΈ
4
1
#15 opened 13 days ago
by
md-1415
Amazing model
π
β€οΈ
2
#14 opened 15 days ago
by
leniad
Experience on finetuning for specific language
2
#13 opened 15 days ago
by
Huy227
Fix typo in model architecture class name
2
#12 opened 15 days ago
by
Xenova
Apple users fear not you can use MLX too!
π
π₯
6
1
#11 opened 15 days ago
by
pherber3
LightOnOCR-2-1B with Samaritan Hebrew
β€οΈ
3
#10 opened 15 days ago
by
johnlockejrr
any way to get a shrunk output to reduce tokens?
2
#9 opened 16 days ago
by
Mr-Vader
Muliltipage documents
π
2
2
#8 opened 16 days ago
by
jondecker76
Tables as markdown instead of HTML
π
2
5
#6 opened 17 days ago
by
jondecker76
Remove page numbers from the output
1
#5 opened 18 days ago
by
Matthijz98
hallucinations on empty pages
7
#4 opened 18 days ago
by
elenapop
Checkboxes
π
1
#2 opened 18 days ago
by
elenapop
Testing OCR using vllm returns nothing but exclamation marks.
14
#1 opened 18 days ago
by
rsbdev