Inquiry Regarding Fine-Tuned LLaMA 3.3 70B and Potential 4-Bit AWQ Quantized Model Release

#1
by caffeineWoo - opened

I hope this message finds you well.

I was excited to learn about the release of the fine-tuned LLaMA 3.3 70B model and its impressive capabilities. The advancements in fine-tuning are inspiring, and I truly appreciate the efforts your team has made in bringing this model to the community.

I wanted to inquire if there are any plans to release a 4-bit AWQ quantized version of this model. Such a release would undoubtedly enable broader accessibility and practical application, especially for those working with hardware-constrained environments.

Your insights would be greatly appreciated, and I look forward to hearing about any updates or plans for the modelโ€™s development.

Thank you for your time and consideration, and please let me know if thereโ€™s anything further I can assist with or provide feedback on.

ํ•œ๊ตญ๋ถ„์ด์‹ ๊ฐ€์š” ?
๋„ค quantization ํ•ด์„œ ollama์— ๊ณต๊ฐœ ํ•˜์—ฌ ๋“œ๋ฆฌ๊ฒ ์Šต๋‹ˆ๋‹ค.
=Yes, I will make it available on Ollama with quantization.
=ใฏใ„ใ€้‡ๅญๅŒ–ใ—ใฆollamaใงๅ…ฌ้–‹ใ•ใ›ใฆใ„ใŸใ ใใพใ™ใ€‚

ํ•œ๊ตญ๋ถ„์ด์…จ๊ตฐ์š”. ๋ผ๋งˆ 70B ๋ชจ๋ธ์˜ ์ผ๋ณธ์–ด ํ•™์Šต ๋ชจ๋ธ์˜ ํ™œ์šฉ ๊ธฐ๋Œ€๊ฐ€ ํฝ๋‹ˆ๋‹ค. ๊ฐ์‚ฌํ•ฉ๋‹ˆ๋‹ค!!

Sign up or log in to comment