Downloads · 30 days
18
14% of all-time downloads
LLaDA-8B-BGPO-code
THU-KEG/LLaDA-8B-BGPO-code
LLaDA-8B-BGPO-code is a reinforcement learning model from THU-KEG. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
[](https://arxiv.org/abs/2510.11683) [](https://github.com/THU-KEG/BGPO)
All-time downloads
131
Public
Parameters
8B
16 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors16 GB · 100%
At a glance
- Task
- Reinforcement Learning
- License
- apache-2.0
- Model type
- llada
- Access
- Public
- Created
- Oct 11, 2025
- Updated
- Oct 14, 2025
- SHA
- ee75175f
Model card
From the Hugging Face model README
LLaDA-8B-BGPO-code
Model Description
LLaDA-8B-BGPO-code 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 code generation 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: Code generation
- Language: English
Training Details
- Training Epochs: 5 epochs (112 steps per epoch)
- Total Steps: 560 steps
- Response Length: 512 tokens
- Train Diffusion Steps: 512
- 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 code generation tasks.
- Performance may vary on other tasks.
- Requires appropriate computational resources for inference.
- Task
- Reinforcement Learning
- Type
- llada
- License
- apache-2.0
- Languages
- en
- Created
- Oct 11, 2025
- Updated
- Oct 14, 2025