Marius Petruc
InformaticsSolutions
AI & ML interests
None yet
Organizations
None yet
MXFP4 vs Q8 vs bf16
1
#2 opened 2 months ago
by
InformaticsSolutions
Quantization of v2
3
#1 opened 2 months ago
by
kabachuha
Why is granite-docling-258M so slow?
🤝
1
35
#37 opened 4 months ago
by
hgarp-prozis
Docling OCR output
➕
1
5
#38 opened 4 months ago
by
InformaticsSolutions
Suppress the prompt from appearing in the generated response
1
#27 opened almost 2 years ago
by
InformaticsSolutions
slow inference speed
1
#25 opened almost 2 years ago
by
InformaticsSolutions
TypeError: transformers.generation.utils.GenerationMixin.generate() argument after ** must be a mapping, not Tensor
3
#5 opened about 2 years ago
by
Pazuzzu
How much VRAM does this model need?
6
#21 opened about 2 years ago
by
Ziizu
Entity centric reference encoder?
3
#2 opened almost 3 years ago
by
mhill