6 14 152

Alysson Guimarães

k3ybladewielder

AI & ML interests

NLP, Commonsense Reasoning

Recent Activity

liked a model about 5 hours ago

google/gemma-3-1b-it

liked a model about 5 hours ago

unsloth/gemma-3-1b-pt-bnb-4bit

liked a model about 5 hours ago

google/gemma-3-1b-pt

View all activity

Organizations

None yet

k3ybladewielder's activity

liked 3 models about 5 hours ago

New activity in google/gemma-7b about 8 hours ago

Error

#31 opened about 1 year ago by

trungnd7112004

New activity in google/gemma-2b about 8 hours ago

Repo model google/gemma-2b is gated. You must be authenticated to access it.

#28 opened about 1 year ago by

IanKelly63

liked a model about 10 hours ago

google/gemma-7b-it-GGUF

Updated Aug 14, 2024 • 25 • 42

liked a model about 19 hours ago

Qwen/Qwen2-7B-Instruct

Text Generation • Updated Aug 21, 2024 • 273k • • 621

liked a dataset 1 day ago

nilc-nlp/assin2

Viewer • Updated Jan 9, 2024 • 9.45k • 910 • 14

liked a model 2 days ago

facebook/bart-large-mnli

Zero-Shot Classification • Updated Sep 5, 2023 • 2.88M • • 1.32k

liked a model 4 days ago

google/bigbird-pegasus-large-pubmed

Summarization • Updated Jan 24, 2023 • 1.74k • • 46

reacted to clem's post with 🔥 4 days ago

Post

7014

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!