rtuuuuuuuur
urtuuuu
AI & ML interests
None yet
Organizations
None yet
urtuuuu's activity
On some promts, medium is worse than mini&small?
6
#2 opened about 1 month ago
by
urtuuuu
MMLU Lower Results Theory
3
#5 opened about 1 month ago
by
fblgit
![](https://cdn-avatars.huggingface.co/v1/production/uploads/6401c8c9f98fbc64bcd7dca1/MOSgc_mPbfUZ-354osy1v.png)
Promt format question
2
#1 opened about 1 month ago
by
urtuuuu
One of the best LLM I tested so far. And it runs fast on 3090
2
#1 opened about 2 months ago
by
victorx98
Passes "snake in python test" after only 3 attempts
2
#1 opened about 2 months ago
by
rombodawg
![](https://cdn-avatars.huggingface.co/v1/production/uploads/642cc1c253e76b4c2286c58e/fGtQ_QeTjUgBhIT89dpUt.jpeg)
Reasoning?
1
#6 opened about 2 months ago
by
urtuuuu
Gibberish after ~2k ctx
#3 opened 2 months ago
by
urtuuuu
Maybe a silly question...
2
#18 opened 2 months ago
by
urtuuuu
OK llama 3 8b model is INSANE. Is almost as good as wizard 2 8x22b!
52
#5 opened 2 months ago
by
mirek190
Working with llama cpp ?
4
#1 opened 2 months ago
by
ivanpzk
Is it really good?
5
#20 opened 2 months ago
by
urtuuuu
Doesn't work in oobabooga
8
#1 opened 2 months ago
by
urtuuuu
Exlama2?
6
#1 opened 9 months ago
by
hunty1
chat-instruct mode
#1 opened 6 months ago
by
urtuuuu