Alberto Cetoli PRO

fractalego's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model about 22 hours ago

Zyphra/Zonos-v0.1-hybrid

Text-to-Speech • Updated 1 day ago • 874 • 501

liked a model 9 days ago

Almawave/Velvet-14B

Text Generation • Updated 44 minutes ago • 3.44k • 114

upvoted an article 9 days ago

view article

Article

Open-R1: Update #1

By and 7 others •

10 days ago

• 268

liked a model 10 days ago

iGeniusAI/Italia-9B-Instruct-v0.1

Text Generation • Updated Jul 23, 2024 • 9.53k • 50

upvoted an article 12 days ago

view article

Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

By •

Jul 5, 2024

• 199

upvoted a paper 15 days ago

DeepSeek-V3 Technical Report

Paper • 2412.19437 • Published Dec 27, 2024 • 50

upvoted a paper 26 days ago

Towards Best Practices for Open Datasets for LLM Training

Paper • 2501.08365 • Published 28 days ago • 54

upvoted an article 27 days ago

view article

Article

Visualize and understand GPU memory in PyTorch

Dec 24, 2024

• 183

liked a dataset 28 days ago

liminghao1630/TableBank

Updated Aug 11, 2024 • 306 • 9

liked a model about 1 month ago

stabilityai/stable-video-diffusion-img2vid-xt

Image-to-Video • Updated Jul 10, 2024 • 389k • 2.86k

reacted to mitkox's post with 🤯🔥➕ about 1 month ago

view post

Post

2470

Can it run DeepSeek V3 671B is the new 'can it run Doom'.

How minimalistic can I go with on device AI with behemoth models - here I'm running DeepSeek V3 MoE on a single A6000 GPU.

Not great, not terrible, for this minimalistic setup. I love the Mixture of Experts architectures. Typically I'm running my core LLM distributed over the 4 GPUs.

Make sure you own your AI. AI in the cloud is not aligned with you; it's aligned with the company that owns it.

See translation

• 
• 
• 
• 5 replies

·

🔥

7

7

➕

4

4

🤯

2

2

🤗

1

1

+

Reply

liked 2 datasets about 1 month ago

facebook/winoground

Viewer • Updated Oct 22, 2024 • 400 • 1.12k • 86

agibot-world/AgiBotWorld-Alpha

Viewer • Updated 22 days ago • 19.7M • 22.2k • 168

updated a model about 1 month ago

fractalego/wafl-phi3.5-mini-instruct

Text Generation • Updated Jan 2 • 80

upvoted 3 papers about 2 months ago

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning

Paper • 2411.18203 • Published Nov 27, 2024 • 34

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Paper • 2410.02884 • Published Oct 3, 2024 • 54

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B

Paper • 2406.07394 • Published Jun 11, 2024 • 27

liked a model about 2 months ago

NyxKrage/Microsoft_Phi-4

Updated 26 days ago • 1.54k • 55