FRAMEWIREIndonesiaUpdated Sep 15Live wire
0:00 / 0:00

Wao, this post blew up, and I triggered some Saastophers.

But let me tell you more about SLM fine-tuning. In April-May this year i fine-tuned a 6.5B model: Mac-1 (it controls 487 Mac native apps) My goal was to build a better Siri (and i achieved that). Here's how i

CJ ZafirSep 1569
0:00 / 0:00

China just made AI agents a whole lot cheaper

DeepSeek Harness plus free APIs power agents without the usual costs.

AI Mastery GuideSep 15
0:00 / 0:00

🇨🇳🤖 deepseek engineer on anthropic

“Anthropic having the most powerful AI is like Hitler getting the atomic bomb before the Allies.”

KOSO🇳🇬Sep 153
0:00 / 0:00

I ran two tests on my M5 Max w/ 128GB inside DeepSeek Harness.

On the left is DwarfStar 4 with the 4bit quant. It averaged 52tok/s and took nearly 100 minutes to complete. On the right is MLX-Serve with the 4bit/8bit quant. It averaged 72tok/s and finished in 50 minutes. Both

Rich · Atom Tan StudioSep 15