4 40 373

Bruno Henrique

Bruno

AI & ML interests

None yet

Recent Activity

commented on an article 4 days ago

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

updated a Space 4 days ago

Bruno/gemma-3-12b-pt-br

liked a Space 4 days ago

Bruno/gemma-3-12b-pt-br

View all activity

Organizations

Bruno's activity

commented on Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM 4 days ago

I created a notebook running Gemma 3
https://www.linkedin.com/posts/brunohenriquetech_gemma3-brunohenrique-llm-activity-7306105399684833280-zdkW?utm_source=share&utm_medium=member_desktop&rcm=ACoAABNHABMBzd3izC9J0elGOBiF_YjcEd3F6AI

updated a Space 4 days ago

Gemma 3 12b PT-Br (BH)

🔥

liked 2 Spaces 4 days ago

Gemma 3 12b PT-Br (BH)

🔥

Gemma 3 12b It

🔥

Generate text and analyze images or videos

liked a model 4 days ago

google/gemma-3-1b-pt

Text Generation • Updated 3 days ago • 17.7k • 68

liked a Space 7 days ago

RAG - generate

⚡

Generate text responses to queries

reacted to clem's post with 🔥❤️ 8 days ago

Post

7121

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!