phi3 vision dml
#41 opened about 3 hours ago
by
tinybiggames
![](https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/Vl4fH78BX8evHDi6RFcFg.png)
[Issue] Help with the integration of phi-3-vision on llama.cpp
2
#40 opened about 16 hours ago
by
ManniX-ITA
![](https://cdn-avatars.huggingface.co/v1/production/uploads/65fb32f58a66679f92b73458/ozQW6W27tVCM-SRouzGJa.jpeg)
inference and generation runtime - how to reduce latency
#38 opened 8 days ago
by
wamozart
How to get embedding vectors of images or texts?
1
#37 opened 10 days ago
by
iceleaf97tech
fix-tokenizer
#35 opened 12 days ago
by
xinsu
No support for pipline or TextStreamer
2
#34 opened 17 days ago
by
mohamedlotfy50
Over alignment issues
#33 opened 20 days ago
by
Metricon
![](https://cdn-avatars.huggingface.co/v1/production/uploads/646f1952753be77a8e933f90/OnohCFBLC9aUwqKBTYax8.jpeg)
Handle Batch Sizes (v0.2)
2
#32 opened 20 days ago
by
WilliamSotoM
Shorter context window to reduct inference memory allocation
1
#31 opened 21 days ago
by
JochenGrey
output size of the response is less.
#27 opened 23 days ago
by
anilsnayak
Should Phi-3V provide support in llama.cpp?
5
#24 opened 26 days ago
by
haohoo
Not working on real-life questions
2
#22 opened 27 days ago
by
bh4
Fine-tuning Phi-3-vision on custom dataset fails
9
#21 opened 27 days ago
by
samyak24jain
Endless blank space generation
1
#20 opened 27 days ago
by
mascIT
The image provided does not contain a table.
#19 opened 27 days ago
by
mascIT
How to achieve faster inference speed?
5
#18 opened 28 days ago
by
zkDU
Allow for batch sizes larger than 1.
1
#16 opened 28 days ago
by
sebbyjp
Few Shot
1
#12 opened 30 days ago
by
RicoRausch
the model can't stop generating for content extraction
10
#8 opened about 1 month ago
by
tankstarwar
Finetuning Scripts
8
#5 opened about 1 month ago
by
abrakaa