ansulev/Opus-4.6-Reasoning-2100x-formatted
收藏Hugging Face2026-04-03 更新2026-04-12 收录
下载链接：
https://hf-mirror.com/datasets/ansulev/Opus-4.6-Reasoning-2100x-formatted
下载链接
链接失效反馈官方服务：
资源简介：
---
configs:
- config_name: default
data_files:
- split: train
path: train.parquet
dataset_info:
features:
- name: messages
list:
- name: content
dtype: string
- name: reasoning
dtype: string
- name: role
dtype: string
- name: metadata
struct:
- name: category
dtype: string
- name: difficulty
dtype: string
- name: hash
dtype: string
- name: id
dtype: string
- name: model
dtype: string
- name: source_dataset
dtype: string
- name: timestamp
dtype: string
splits:
- name: train
num_bytes: 6887425
num_examples: 2160
---
[[<img src="https://huggingface.co/crownelius/Crow-9B-Opus-4.6-Distill-Heretic_Qwen3.5/resolve/main/banner.png" width="350"/>](https://ko-fi.com/abcuo)](https://ko-fi.com/abcuo)
# Opus-4.6-Reasoning-2100x (TeichAI Format)
Formatted to match `TeichAI/claude-4.5-opus-high-reasoning-250x` format.
## Source
- **Original**: `crownelius/Opus-4.6-Reasoning-2100x`
- **Original Examples**: 2160
- **Converted Examples**: 2160
## Format
```json
{
"messages": [
{"role": "system", "content": "..."},
{"role": "user", "content": "..."},
{"role": "assistant", "content": "..."}
],
"metadata": {...}
}
```
## Files
- `train.jsonl` (7.09 MB)
- `train.parquet` (3.44 MB)
Converted on 2026-02-15.
---
## Stats
| Metric | Value |
|--------|-------|
| Total prompt tokens | 226,879 |
| Total completion tokens | 751,264 |
| Total tokens | 978,143 |
| Total cost | $19.92 (USD) |
| Average turns | 1.00 |
| Average tool calls | 0.00 |
| Average tokens per row | 226.42 |
*Cost estimated using Claude Opus 4.6 pricing on [OpenRouter](https://openrouter.ai) ($5.0/M input, $25.0/M output)*
提供机构：
ansulev
