Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Building on HF
5
2
2
Martins Udris
PRO
martinsu
Follow
sverns's profile picture
towmasjan's profile picture
attacker05's profile picture
18 followers
·
7 following
AI & ML interests
None yet
Recent Activity
replied
to
etemiz
's
post
12 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
13 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
14 days ago
mistralai/Devstral-Small-2-24B-Instruct-2512:
FP16 Weights
View all activity
Organizations
None yet
martinsu
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
24 days ago
utter-project/EuroLLM-22B-Instruct-2512
Text Generation
•
23B
•
Updated
26 days ago
•
46.1k
•
•
42
liked
a model
3 months ago
TildeAI/TildeOpen-30b
Text Generation
•
31B
•
Updated
Oct 8, 2025
•
2.3k
•
143