raca-workspace-v1/grpo-tool-sat-sft-corpus-v1
收藏Hugging Face2026-04-19 更新2026-04-26 收录
下载链接：
https://hf-mirror.com/datasets/raca-workspace-v1/grpo-tool-sat-sft-corpus-v1
下载链接
链接失效反馈官方服务：
资源简介：
---
license: mit
tags:
- grpo-tool-saturation
- sft
- llamafactory-ready
---
# grpo-tool-sat-sft-corpus-v1
SFT-only view of grpo-tool-sat-dataset-v1. v1.1 — prompt now ends with newline to match RL eval_prefix concatenation.
## Dataset Info
- **Rows**: 8000
- **Columns**: 5
## Columns
| Column | Type | Description |
|--------|------|-------------|
| k | Value('int64') | Key integer |
| r | Value('int64') | k mod 3 |
| tool | Value('string') | map or table |
| prompt | Value('string') | User prompt: "Key: <k>
" (trailing newline) |
| response | Value('string') | Target completion: prose + <tool_call> + <observation> + <answer> |
## Generation Parameters
```json
{
"script_name": "src/data_gen.py + filter",
"model": "n/a",
"description": "SFT-only view of grpo-tool-sat-dataset-v1. v1.1 \u2014 prompt now ends with newline to match RL eval_prefix concatenation.",
"hyperparameters": {
"seed": 1,
"overlap_skew_map": 0.6,
"hash_slice": 6
},
"input_datasets": [
"raca-workspace-v1/grpo-tool-sat-dataset-v1"
]
}
```
## Usage
```python
from datasets import load_dataset
dataset = load_dataset("raca-workspace-v1/grpo-tool-sat-sft-corpus-v1", split="train")
print(f"Loaded {len(dataset)} rows")
```
---
*Uploaded via [RACA](https://github.com/Zayne-sprague/Dr-Claude-Code) hf_utility.*
提供机构：
raca-workspace-v1
