Model Selection

Reinforcement learning inference

# Reinforcement learning inference

Deepseek R1 Distill Qwen 32B Unsloth Bnb 4bit

DeepSeek-R1 is the first-generation inference model launched by the DeepSeek team. Through large-scale reinforcement learning training, it does not require supervised fine-tuning (SFT) as an initial step and demonstrates excellent inference capabilities.

Large Language Model

Transformers English

Featured Recommended AI Models

AIbase

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

© 2025AIbase