# Subnet 96 — Clean Q/A Dataset

**Format:** one JSONL per line:
```json
{"system": null, "conversations":[{"role":"user","content":"..."}, {"role":"assistant","content":"..."}]}
```

- **Total pairs:** 2
- **Avg answer length (tokens):** 27.5 (median 27.5, min 25, max 30)
- **Schema errors:** 0 (should be 0)
- **File size:** 0.00 MB
- **SHA256 (data.jsonl):** `4d28dd4534eaa107115068d18fe22862b926bc1503a1b45f6709a223cfac3a5a`

> Language: **English**
> Intended for: **Bittensor Subnet 96 validators**
> Generation: local LLaMA (GPU) + cleaning/normalization scripts.