Qwen3-4B-SFT-DPO-4B-1409i-beta0.15-sft0.3-lr1e-6-bs32-ep3-step-120

Description

Qwen3-4B-SFT-DPO-4B-1409i-beta0.15-sft0.3-lr1e-6-bs32-ep3-step-120 is an open-weight text-generation model with roughly 4B parameters published by code-critic-model on the Hugging Face Hub. It has 286 downloads. Runs with transformers.

Categories

• Coding
• Productivity

Tags

• qwen3
• text-generation
• dpo
• trl
• code-critic
• process-reward-model
• conversational

Capabilities

• Text generation
• Conversational
• Library: transformers
• 4B parameters