metadata
license: mit
language:
- en
library_name: transformers
tags:
- reinforcement-learning
- factuality
- grounding
- verifiable-ai
- ERRL
- fp4
- variant
- fine-tune
base_model:
- deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
metrics:
- accuracy
datasets:
- eclipse-ai/eclipse-news-dataset
- eclipse-ai/eclipse-synthetic-dataset
- eclipse-ai/eclipse-common-crawl-filtered