Hugging Face's logo

microsoft
/
Phi-3.5-vision-instruct

Image-Text-to-Text
Transformers
Safetensors
multilingual
phi3_v
text-generation
nlp
code
vision
conversational
custom_code
Model card Files Community
32

Ollama availability

#8
by ramesh3012 - opened
Discussion
ramesh3012

Hi,

    I wanted to see this model available in ollama. Can you please let me know when it will be available?

Thanks
Ramesh Rajamani

haohoo

Unfortunately, llama.cpp currently does not support some techs like LongRoPE, Flash attention, CLIP ViT projector, etc which used by Phi-3... Ollama uses llama.cpp as infra. So...

haohoo

Unfortunately, llama.cpp currently does not support some techs like LongRoPE, Flash attention, CLIP ViT projector, etc which used by Phi-3... Ollama uses llama.cpp as infra. So...

Looks like I made a mistake... llava-phi3 on ollama can use CLIP ViT model as part of gguf model files. And combine with the Phi-3 text model. I just meet issues when I try to convert Phi-3/3.5 vision to GGUF by llama.cpp.

Sign up or log in to comment