14B Perceived Pattern
Collection
Experimentals
•
5 items
•
Updated
•
1
Prithiv Sakthi
prithivMLmods
AI & ML interests
computer vision, multimodality, adapters @starngerzonehf @strangerguardhf
Recent Activity
upvoted
a
collection
about 3 hours ago
14B Perceived Pattern
published
a model
about 3 hours ago
prithivMLmods/APM-08279-5255-14B
updated
a model
about 3 hours ago
prithivMLmods/APM-08279-5255-14B
Organizations
prithivMLmods's activity
upvoted
a
collection
about 3 hours ago
published
a
model
about 3 hours ago
updated
a
model
about 3 hours ago
liked
a
model
about 3 hours ago
published
a
model
about 3 hours ago
updated
a
model
about 3 hours ago
published
a
model
about 3 hours ago
updated
2
models
about 3 hours ago
updated
a
model
about 4 hours ago
updated
a
Space
about 4 hours ago
Multilingual Proficiency - which languages?
8
#2 opened 1 day ago
by
mmbela
updated
a
Space
about 16 hours ago
published
2
models
about 17 hours ago
updated
a
Space
about 17 hours ago
updated
a
Space
about 18 hours ago
reacted to
clem's
post with 🔥
about 19 hours ago
Post
2514
I was chatting with
@peakji
, one of the cofounders of Manu AI, who told me he was on Hugging Face (very cool!).
He shared an interesting insight which is that agentic capabilities might be more of an alignment problem rather than a foundational capability issue. Similar to the difference between GPT-3 and InstructGPT, some open-source foundation models are simply trained to 'answer everything in one response regardless of the complexity of the question' - after all, that's the user preference in chatbot use cases. Just a bit of post-training on agentic trajectories can make an immediate and dramatic difference.
As a thank you to the community, he shared 100 invite code first-come first serve, just use “HUGGINGFACE” to get access!
He shared an interesting insight which is that agentic capabilities might be more of an alignment problem rather than a foundational capability issue. Similar to the difference between GPT-3 and InstructGPT, some open-source foundation models are simply trained to 'answer everything in one response regardless of the complexity of the question' - after all, that's the user preference in chatbot use cases. Just a bit of post-training on agentic trajectories can make an immediate and dramatic difference.
As a thank you to the community, he shared 100 invite code first-come first serve, just use “HUGGINGFACE” to get access!
- 5 replies
updated
a
Space
about 19 hours ago
gguf problem after conversion by llama.cpp
2
#1 opened 1 day ago
by
mmbela