venkat's picture

6 5

venkat

sloshywings

·

gella

AI & ML interests

homeostatic balance of doshas to attain living moksha

Recent Activity

replied to lewtun's post 3 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! 🧪 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

updated a model 6 days ago

thirdeyeai/DeepSeek-R1-Distill-Qwen-1.5B-uncensored

updated a model 6 days ago

thirdeyeai/DeepSeek-R1-Distill-Qwen-14B-uncensored

View all activity

Organizations

sloshywings's activity

liked a model 2 months ago

THUDM/glm-edge-v-5b

Image-Text-to-Text • Updated 28 days ago • 213 • 11

liked a Space 2 months ago

Boltz 1

Boltz-1

liked 2 models 3 months ago

thirdeyeai/llama3.2-3b-uncensored

Text Generation • Updated Nov 9, 2024 • 201 • 1

thirdeyeai/qwen2.5-.5b-uncensored

Text Generation • Updated 8 days ago • 175 • 1

liked a dataset 3 months ago

neuralwork/arxiver

Viewer • Updated Nov 1, 2024 • 63.4k • 376 • 358