In Honour of This Year's NeurIPs Test of Time Paper Awardees
•
2
Jaward Sesay
Jaward
AI & ML interests
I like to train large deep neural nets too 🧠🤖💥 | First Paper (AutoAgents: A Framework for Automatic Agent Generation) Accepted @ IJCAI 2024 | Role Model Karpathy
Recent Activity
liked
a Space
about 23 hours ago
webml-community/deepseek-r1-webgpu
posted
an
update
4 days ago
"the power and beauty of reinforcement learning: rather than explicitly teaching the model on how to solve a problem, we simply provide it with the right incentives, and it autonomously develops advanced problem-solving strategies", deepseek researchers are so based🔥
They had an “aha moment”, a key takeaway from this is to always try out new ideas from first-principles.
Paper: https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf
Code: https://github.com/deepseek-ai/DeepSeek-R1
Weights: https://huggingface.co/collections/deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d
upvoted
a
paper
5 days ago
Evolving Deeper LLM Thinking
Articles
Organizations
Posts
70
Post
424
"the power and beauty of reinforcement learning: rather than explicitly teaching the model on how to solve a problem, we simply provide it with the right incentives, and it autonomously develops advanced problem-solving strategies", deepseek researchers are so based🔥
They had an “aha moment”, a key takeaway from this is to always try out new ideas from first-principles.
Paper: https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf
Code: https://github.com/deepseek-ai/DeepSeek-R1
Weights: deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d
They had an “aha moment”, a key takeaway from this is to always try out new ideas from first-principles.
Paper: https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf
Code: https://github.com/deepseek-ai/DeepSeek-R1
Weights: deepseek-ai/deepseek-r1-678e1e131c0169c0bc89728d
Post
1842
minimal single script implementation of knowledge distillation in LLMs. In this implementation, we use GPT-2 (124M) as student model and GPT-2 Medium (340M) as teacher via reverse Kullback-Leibler (KL) divergence, trained on a small chunk of openwebtext.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/llm_knowledge_distillation.ipynb
Code: https://github.com/Jaykef/ai-algorithms/blob/main/llm_knowledge_distillation.ipynb
Papers
1
models
3
datasets
None public yet