Eugenio Schiavoni

Kukedlc

https://www.linkedin.com/in/eugenio-schiavoni/

AI & ML interests

LLM, Computer Vision, Forecast, Neural Muse (EEG), ML for EEG, Cognitive Artificial Intelligence, Neurophysiology, Experimental Psychobiology, Consciousness and Philosophy, Linguistics, Arts, among others.

Recent Activity

updated a model 13 days ago

Kukedlc/NeuralQwen-7B-Spanish-Iptel

published a model 13 days ago

Kukedlc/NeuralQwen-7B-Spanish-Iptel

liked a model 14 days ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

View all activity

Organizations

Kukedlc's activity

updated a model 13 days ago

Kukedlc/NeuralQwen-7B-Spanish-Iptel

private

Updated 13 days ago • 4

published a model 13 days ago

Kukedlc/NeuralQwen-7B-Spanish-Iptel

private

Updated 13 days ago • 4

liked a model 14 days ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • Updated 1 day ago • 1.15M • • 934

updated a model 25 days ago

Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3

Text Generation • Updated 25 days ago • 6.28k • 2

liked a model 25 days ago

TIGER-Lab/Qwen2.5-Math-7B-CFT

Text Generation • Updated 24 days ago • 121 • 6

liked a dataset 25 days ago

TIGER-Lab/WebInstruct-CFT

Viewer • Updated 24 days ago • 654k • 1.09k • 41

liked a model 26 days ago

mistralai/Mistral-Small-24B-Instruct-2501

Text Generation • Updated 23 days ago • 755k • • 818

liked 2 models 27 days ago

m-a-p/YuE-s1-7B-anneal-en-cot

Text Generation • Updated 26 days ago • 127k • 379

deepseek-ai/Janus-Pro-1B

Any-to-Any • Updated 24 days ago • 123k • 383

upvoted an article 27 days ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

29 days ago

• 773

liked a model 27 days ago

Qwen/Qwen2.5-VL-3B-Instruct

Image-Text-to-Text • Updated 10 days ago • 519k • 228

liked a dataset 28 days ago

open-thoughts/OpenThoughts-114k

Viewer • Updated 5 days ago • 228k • 109k • 602

liked 2 models 29 days ago

deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated 24 days ago • 490k • 3.12k

Qwen/Qwen2.5-Math-7B

Text Generation • Updated Sep 23, 2024 • 211k • 59

liked 2 models 30 days ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

Text Generation • Updated 1 day ago • 914k • 492

Qwen/Qwen2.5-7B-Instruct-1M

Text Generation • Updated 27 days ago • 298k • 241

liked a dataset about 1 month ago

bespokelabs/Bespoke-Stratos-17k

Viewer • Updated 26 days ago • 16.7k • 96.5k • 280

reacted to lewtun's post with 🤗🔥🚀 about 1 month ago

Post

10164

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open!

🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1.

🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code.

🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training.

Follow along: https://github.com/huggingface/open-r1

5 replies