2848fa16-fa00-4e33-9d9c-f9e7e9d19a74

image

This model was pre-trained from scratch using a dataset of under 20k samples.
As this is an early test version, hallucinations may occur frequently.
To improve speed and performance, a new architecture and computation methods have been developed.
The project aims to develop a lightweight and fast model using minimal training data.
Once the model reaches a level suitable for commercial use, actual running examples will be released.

I’m an independent developer building and maintaining AI projects on my own.
Everything from model development to server costs, datasets, and feature updates is managed personally.
Any support you can provide greatly helps keep this project running and allows for continuous improvements.
If you find this project helpful, please consider supporting my work. Thank you.

이 λͺ¨λΈμ€ 20k 미만의 μ†Œκ·œλͺ¨ 데이터셋을 ν™œμš©ν•΄ μ²˜μŒλΆ€ν„° 사전 ν•™μŠ΅λ˜μ—ˆμŠ΅λ‹ˆλ‹€.
ν˜„μž¬λŠ” ν…ŒμŠ€νŠΈ λ‹¨κ³„λ‘œ ν• λ£¨μ‹œλ„€μ΄μ…˜ ν˜„μƒμ΄ 자주 λ°œμƒν•  수 μžˆμŠ΅λ‹ˆλ‹€.
속도와 μ„±λŠ₯ ν–₯상을 μœ„ν•΄ μƒˆλ‘œμš΄ μ•„ν‚€ν…μ²˜μ™€ μ—°μ‚° 방법을 κ°œλ°œν•˜μ˜€μŠ΅λ‹ˆλ‹€.
적은 λ°μ΄ν„°λ‘œλ„ 가볍고 λΉ λ₯΄κ²Œ κ΅¬λ™λ˜λŠ” λͺ¨λΈμ„ λͺ©ν‘œλ‘œ 개발 μ€‘μž…λ‹ˆλ‹€.
λͺ¨λΈμ΄ μƒμš©ν™”ν•  수 μžˆλŠ” μˆ˜μ€€μ— λ„λ‹¬ν•˜λ©΄ μ‹€μ œ ꡬ동 예제λ₯Ό κ³΅κ°œν•  μ˜ˆμ •μž…λ‹ˆλ‹€.

ν˜Όμžμ„œ AI ν”„λ‘œμ νŠΈλ₯Ό κ°œλ°œν•˜κ³  μš΄μ˜ν•˜κ³  μžˆμŠ΅λ‹ˆλ‹€.
λͺ¨λΈ κ°œλ°œλΆ€ν„° 데이터셋 μ€€λΉ„, μ„œλ²„ λΉ„μš© 감당, κΈ°λŠ₯ μ—…λ°μ΄νŠΈκΉŒμ§€ λͺ¨λ‘ 직접 μ§„ν–‰ν•˜κ³  μžˆμŠ΅λ‹ˆλ‹€.
λ³΄λ‚΄μ£Όμ‹œλŠ” λ”°λœ»ν•œ 후원은 μ•ˆμ •μ μΈ μ„œλΉ„μŠ€ μœ μ§€μ™€ μƒˆλ‘œμš΄ κΈ°λŠ₯ κ°œλ°œμ— 큰 도움이 λ©λ‹ˆλ‹€.
ν”„λ‘œμ νŠΈκ°€ λ§ˆμŒμ— λ“œμ…¨λ‹€λ©΄ ν›„μ›μœΌλ‘œ 응원해 μ£Όμ‹œλ©΄ κ°μ‚¬ν•˜κ² μŠ΅λ‹ˆλ‹€.

문의 : a@099.kr

ko-fi

45d0e5b5-5fab-4923-a3a0-d9e19949cc03

Downloads last month
274
Safetensors
Model size
63.6M params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Collection including aixk/vlite3.5-nano-RURU-63M