t2ance/bilevel-grpo-4b-step110-bestofn-qwen3_30b

---
license: apache-2.0
size_categories:
- 1K<n<10K
tags:
- code-verification
- llm-judge
- multi-model
- selection
configs:
- config_name: qwen3_30b
data_files:
- split: train
path: "data/qwen3_30b/*.parquet"
---

# CodeRM LLM Judge Trajectories (Multi-Model)

## Dataset Description

This dataset contains selection trajectories from multiple model solutions evaluated by an LLM judge.

## Available Splits

| Split | Trajectories |
|-------|-------------|
| qwen3_30b | 1,048 |

**Total**: 1,048 trajectories across 1 models

## Usage

```python
from datasets import load_dataset

# Load all splits
ds = load_dataset("t2ance/bilevel-grpo-4b-step110-bestofn-qwen3_30b")

# Load specific split
ds = load_dataset("t2ance/bilevel-grpo-4b-step110-bestofn-qwen3_30b", split="qwen3_30b")
```

## License

Apache 2.0