DeepSeek-R1-8B-PolySurgery

Description

DeepSeek-R1-8B-PolySurgery is an open-weight text-generation model with roughly 8B parameters published by aecetin on the Hugging Face Hub. It has 477 downloads.

Categories

• Research

Tags

• deepseek_r1_polysurgery
• deepseek-r1
• reasoning
• llama-8b
• closed-form-solver
• in-situ-weight-surgery
• chebyshev-polynomial
• idempotent-poly

Capabilities

• Text generation
• 8B parameters