Model description
Bu model Core-2.0 asosida o‘zbek tilida multimodal savol-javob tizimi uchun o‘qitilgan. Model quyidagi funksiyalarni qo‘llab-quvvatlaydi:
- Matn savol → Matn javob
- Rasm → Javob
- Rasm + Savol → Javob
- Agar foydalanuvchi jami 20 000 so‘mdan ortiq to‘lov qilgan bo‘lsa, javobni ovozli holda ham oladi.
Model turli kirish turlarini birlashtirgan holda (matn, rasm, ovoz) javob qaytaradi. U o‘zbek tili uchun moslashtirilgan va real ilovalar, yordamchi botlar yoki mobil dasturlar uchun foydalidir.
Trigger words
You should use uzbek to trigger the image generation.
You should use multimodal to trigger the image generation.
You should use image captioning to trigger the image generation.
You should use BLIP-2 to trigger the image generation.
You should use o‘zbekcha to trigger the image generation.
You should use vision-language to trigger the image generation.
You should use chatbot to trigger the image generation.
You should use assistant to trigger the image generation.
You should use image-to-text to trigger the image generation.
You should use text-to-text to trigger the image generation.
You should use audio-to-text to trigger the image generation.
You should use blip2-uzbek to trigger the image generation.
Download model
Download them in the Files & versions tab.
