@embw_l0x i wonder what the $60 on gets. like 3 total prompts, and two of them are hello and the other limited to a 140 char tweet lol.
i like the grok plan, it feels fair to me.
🚀 Meet MiniCPM5-2B, a 2B-parameter language model bringing high intelligence density to the edge, now open source!
It ranks #1 among open-source models under 4B parameters on the
@ArtificialAnlys Intelligence Index, with a score of 23.
It also scores 20 on the Agentic Index, bringing an early form of general-purpose agent capability to the edge.
Across 34 benchmarks, MiniCPM5-2B achieves an average score of 53.9, covering coding, math, long-context understanding, tool use, and agentic tasks.
And this release goes beyond the model itself.
We’re opening up the data, training recipes, and RL stack behind MiniCPM5-2B.
🤗 Hugging Face: https://t.co/FZOMTZhBjq
💻 GitHub: https://t.co/2L0I8bYv8f
Modelscope: https://t.co/WRlPNEAzgu
Web: https://t.co/gRSu65FeZL
@Blackwellboy@CYBRTERPS Dude, some company released the entire training set for their model, I'm gonna have to buy a hard drive. Literally lol. I'm gonna make a model, ya know what i mean? it'll take it's little turns on the cat walk...
@EmmyBearAI@CodeWithTamara Soemthing I learnt was comparisons are rarely useful unless they are with your former self, and when you look forward you will only ever see people ahead of you - but you go where you look, so forward it must be!
@cryptosibbers@CodeWithTamara Frank, that's way better worded than I could do, dude. It's nice to see where I want to be and know it is actually obtainable.
@CodeWithTamara i follow is great and their rewards are well deserved. i appreciate the humor, the kind words, the advice, and i wish you guys all success.
also, i shouldn't post stoned.