Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
2
2
6
michael ilie
PRO
skdrx
Follow
Hicham04's profile picture
1 follower
·
4 following
mcilie
AI & ML interests
None yet
Recent Activity
reacted
to
etemiz
's
post
with 👀
8 days ago
-= DeepSeek V3 =- After installing the new CUDA toolkit and compiling llama.cpp again I tested DeepSeek V3 yesterday. In terms of human alignment DeepSeek V3 did worse on: - health - fasting - nostr - misinfo - nutrition did better on: - faith - bitcoin - alternative medicine - ancient wisdom compared to DeepSeek 2.5. In my opinion overall it is worse than 2.5. And 2.5 wasn't that great. There is a general tendency of models getting smarter but at the same time getting less wiser, less human aligned, less beneficial to humans. I don't know what is causing this. But maybe synthetic dataset use for further training the LLMs makes it more and more detached from humanity. This is not going in the right direction. My solution is to come up with a curator council to determine the datasets that are closest to human preference. "Humans that care about other humans the most" could be a definition of this dataset. What do you think?
updated
a dataset
about 2 months ago
skdrx/python-dpo-dataset-complete-just-formatting
updated
a dataset
about 2 months ago
skdrx/python-dpo-dataset-varname
View all activity
Organizations
skdrx
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
liked
a model
4 months ago
mistralai/Pixtral-12B-2409
Image-Text-to-Text
•
Updated
26 days ago
•
581
liked
a model
6 months ago
apple/DCLM-7B
Updated
Jul 26, 2024
•
1.87k
•
829
liked
3 datasets
9 months ago
allenai/dolma
Updated
Apr 17, 2024
•
854
•
867
togethercomputer/RedPajama-Data-1T
Viewer
•
Updated
Jun 17, 2024
•
1.73M
•
933
•
1.07k
vikp/textbook_quality_programming
Viewer
•
Updated
Oct 8, 2023
•
11.7k
•
117
•
179
liked
a dataset
about 1 year ago
PromptSystematicReview/ThePromptReport
Updated
Jun 14, 2024
•
1.03k
•
34