Hugging Face's logo
venkat's picture
6 5

venkat

sloshywings
DataSoul's profile picture 21world's profile picture avishetty's profile picture
Ā·

AI & ML interests

homeostatic balance of doshas to attain living moksha

Recent Activity

replied to lewtun's post 2 days ago
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! šŸ§Ŗ Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1. šŸ§  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. šŸ”„ Step 3: show we can go from base model -> SFT -> RL via multi-stage training. Follow along: https://github.com/huggingface/open-r1
updated a model 5 days ago
thirdeyeai/DeepSeek-R1-Distill-Qwen-1.5B-uncensored
updated a model 5 days ago
thirdeyeai/DeepSeek-R1-Distill-Qwen-14B-uncensored
View all activity

Organizations

thirdeye Ai's profile picture

Posts 1