Hugging Face's logo
Martins Udris's picture
Building on HF
5 2 2

Martins Udris PRO

martinsu
webxos's profile picture Julian-Dumitrascu's profile picture m20l22's profile picture
·

AI & ML interests

None yet

Recent Activity

replied to etemiz's post 9 days ago
I realized when I ask longer answers to my questions, the models sometimes produce completely opposite answer. What could be the reason? I do mostly CPT. Should I convert my dataset to SFT and give longer reasonings too for it to have integrity? Example: Is the yolk of an egg more beneficial or the white? Answer in 100 words. Answer: Yolk is more beneficial because .......... Example: Is the yolk of an egg more beneficial or the white? Answer in 500 words. Answer: White is more beneficial because .......... Edit: These happen in temp = 0.0
replied to etemiz's post 10 days ago
I realized when I ask longer answers to my questions, the models sometimes produce completely opposite answer. What could be the reason? I do mostly CPT. Should I convert my dataset to SFT and give longer reasonings too for it to have integrity? Example: Is the yolk of an egg more beneficial or the white? Answer in 100 words. Answer: Yolk is more beneficial because .......... Example: Is the yolk of an egg more beneficial or the white? Answer in 500 words. Answer: White is more beneficial because .......... Edit: These happen in temp = 0.0
new activity 11 days ago
mistralai/Devstral-Small-2-24B-Instruct-2512:FP16 Weights
View all activity

Organizations

None yet