logoalt Hacker News

armcat01/20/20251 replyview on HN

I tried one of their "distill" versions on HF Spaces: https://huggingface.co/spaces/Aratako/DeepSeek-R1-Distill-Qw.... It seems to suffer from the same old repetition and overthinking problems. Using the classic strawberry sniff test:

... Wait, did I count correctly? Let me recount. The word is S-T-R-A-W-B-E-R-R-Y. So positions 3, 8, and 9 are 'R's. That makes three 'R's in total. But I'm a bit confused because when I first wrote it out, I thought maybe only two. Let me double-check. Maybe I miscounted the letters.

Alternatively, perhaps the word doesn't have three 'R's. Let me write it again: S-T-R-A-W-B-E-R-R-Y. So, after E, there are two R's before Y. So that would be two R's, right? Wait, no, in the breakdown, position 3 is R, then position 8 and 9 are R's. So that's three R's. But I'm not sure if that's correct because sometimes people might miscount. ...


Replies

do_anh_tu01/21/2025

When I ran the DeepSeek-R1-Distill-Qwen-32B-Q4_0.ggu[1] version in Ollama, it got the strawberry test right, but when I paste that same question to OpenWebUI, it got wrong as you got here.

[1] https://huggingface.co/bartowski/DeepSeek-R1-Distill-Qwen-32...