metadata
license: mit
base_model:
- deepseek-ai/DeepSeek-R1-Zero
pipeline_tag: text-generation
tags:
- devquasar
DeepSeek-R1 BF16 version
from original model card:
Model | #Total Params | #Activated Params | Context Length | Download |
---|---|---|---|---|
DeepSeek-R1-Zero | 671B | 37B | 128K | 🤗 HuggingFace |