[MODEL REQUEST] Phi 3.5 Vision

NexaAI / nexa-sdk

Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-speech (TTS) capabilities.

https://docs.nexaai.com/

Apache License 2.0

1.51k stars 209 forks source link

[MODEL REQUEST] Phi 3.5 Vision #118

Open aretrace opened 1 week ago

aretrace commented 1 week ago

Model Description

microsoft/Phi-3.5-vision-instruct

Model Resources

https://huggingface.co/microsoft/Phi-3.5-vision-instruct

zhiyuan8 commented 1 week ago

Thanks for raising this request, @aretrace , this VLM support is on our roadmap.