metadata
license: apache-2.0
language:
- en
tags:
- reinforcement-learning
- mathematics
- dllm
- bgpo
- llada
size_categories:
- 8B
LLaDA-8B-BGPO-math
Model Description
LLaDA-8B-BGPO-math is an 8-billion parameter diffusion large language model (dLLM) that was trained on LLaDA-8B-Instruct using Boundary-Guided Policy Optimization (BGPO) for enhanced mathematical capabilities.
Model Details
- Model Type: Diffusion Large Language Model (dLLM)
- Parameters: 8 billion
- Training Method: Boundary-Guided Policy Optimization (BGPO)
- Base Model: LLaDA-8B-Instruct
- Task: Mathematics
- Language: English
Training Details
- Training Steps: 700 steps
- Response Length: 512 tokens
- Train Diffusion Steps: 256
- Eval Diffusion Steps: 512
- Block Size: 32
- Monte Carlo Sample Size ($n_t$): 16
- Learning Rate: 5e-7
- Batch Size: 16
- Framework: Built on VeRL (Volcengine Reinforcement Learning)
Usage & Limitations
- Primarily designed for mathematical tasks.
- Performance may vary on other tasks.
- Requires appropriate computational resources for inference.