Post
We just crossed 1,500,000 public models on Hugging Face (and 500k spaces, 330k datasets, 50k papers). One new repository is created every 15 seconds. Congratulations all!
Clem 🤗 PRO
clem
AI & ML interests
multi-modal, time-series, biology and chemistry
Recent Activity
liked
a Space
44 minutes ago
jasperai/LBM_relighting
liked
a model
about 2 hours ago
mradermacher/TinyDolphin-2.8.2-1.1b-GGUF
Organizations
Posts
44
Post
6971
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!
Collections
3
-
Attention Is All You Need
Paper • 1706.03762 • Published • 55 -
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Paper • 1810.04805 • Published • 17 -
Universal Language Model Fine-tuning for Text Classification
Paper • 1801.06146 • Published • 6 -
Language Models are Few-Shot Learners
Paper • 2005.14165 • Published • 13
spaces
5
models
9
clem/ai-french-prime-minister
Updated
•
19
clem/gemini
Updated
•
90
clem/test
Updated
clem/maxdekdt
Text-to-Image
•
Updated
•
10
•
3
clem/friedeberg
Text-to-Image
•
Updated
•
33
clem/autonlp-test3-2101787
Text Classification
•
Updated
•
120
clem/autonlp-test3-2101782
Text Classification
•
Updated
•
120
clem/autonlp-test3-2101779
Text Classification
•
Updated
•
128
clem/bert_portuguese
Updated
•
1