DeepSeekR1DistillLlama
8B|70B
OverviewDeepSeek-R1-Zero, a reinforcement learning model, shows remarkable reasoning performance but faces challenges. DeepSeek-R1 addresses these issues and matches OpenAI-o1's performance.
Files and versions
Parameters
8B
Quantization
Q5_K_M
Download
Copy
Gaia CLI Command
Copy
Model Metadata
Gaia Domains
Architecture:
-Finetune:
-Parameters:
-Quantization:
-Prompt Template:
-Sign up for updates from the Gaia team
