QwQ-32B is a 32 billion parameter language model achieves comparable performance to DeepSeek-R1 with 671 billion parameters, using reinforcement learning for scaling
QwQ-32B is a 32 billion parameter language model achieves comparable performance to DeepSeek-R1 with 671 billion parameters, using reinforcement learning for scaling
qwenlm.github.io
QwQ-32B: Embracing the Power of Reinforcement Learning
can grab it here
I find it absolutely wild how quickly we went from needing a full blown data centre to run models of this scale to being able to run them on a laptop.
Well that's interesting because I got something completely different locally
<think> Okay, let me figure out how many times the letter "r" appears in the word "strawberry." First, I'll write down the word to visualize it better: S-T-R-A-W-B-E-R-R-Y. Now, I'll go through each letter one by one. Starting with S, T – that's two letters without an R. The third letter is R, so that's one. Then A, W, B, E – those don't have Rs. Next comes another R, making it two. After that, there's another R, bringing the count to three. Finally, the last letters are Y. Wait, let me double-check because sometimes I might miscount. Let me break it down again: S (1), T (2), R (3) – first R here. Then A (4), W (5), B (6), E (7). Next is R again (8) – that's the second R. Another R comes after (9th position?), so third R, and then Y (10). Hmm, maybe I confused the positions. Let me spell it out with numbers: 1. S 2. T 3. R (1st R) 4. A 5. W 6. B 7. E 8. R (2nd R) 9. R (3rd R) 10. Y Yes, so the letters at positions 3, 8, and 9 are Rs. That totals three times. Wait, does "strawberry" have two or three Rs? Let me confirm by spelling it again: S-T-R-A-W-B-E-R-R-Y. Between the B and E, then after that, it's R-R-Y. So there are three Rs total. </think> The letter “r” appears **3 times** in the word "strawberry." Here’s the breakdown: S T **R** A W B E **R** **R** Y Count ’em: 1 (third letter), 2 (eighth letter), and 3 (ninth letter). 🍓