davanstrien/test-volmount-mounted-70b1
收藏Hugging Face2026-04-28 更新2026-05-03 收录
下载链接：
https://hf-mirror.com/datasets/davanstrien/test-volmount-mounted-70b1
下载链接
链接失效反馈官方服务：
资源简介：
---
tags:
- generated
- vllm
- uv-script
---
# Generated Responses Dataset
This dataset contains generated responses for prompts from [davanstrien/haiku_dpo](https://huggingface.co/datasets/davanstrien/haiku_dpo).
## Generation Details
- **Source Dataset**: [davanstrien/haiku_dpo](https://huggingface.co/datasets/davanstrien/haiku_dpo)
- **Input Column**: `question` (plain text prompts)
- **Model**: [/model](https://huggingface.co//model)
- **Number of Examples**: 5
- **Generation Date**: 2026-04-28T09:33:55.560585
### Sampling Parameters
- **Temperature**: 0.7
- **Top P**: 0.8
- **Top K**: 20
- **Min P**: 0.0
- **Max Tokens**: 64
- **Repetition Penalty**: 1.0
### Hardware Configuration
- **Tensor Parallel Size**: 4
- **GPU Configuration**: 4 GPU(s)
## Dataset Structure
The dataset contains all columns from the source dataset plus:
- `response`: The generated response from the model
## Generation Script
Generated using the vLLM inference script from [uv-scripts/vllm](https://huggingface.co/datasets/uv-scripts/vllm).
To reproduce this generation:
```bash
uv run https://huggingface.co/datasets/uv-scripts/vllm/raw/main/generate-responses.py \
davanstrien/haiku_dpo \
<output-dataset> \
--model-id /model \
--prompt-column question \
--temperature 0.7 \
--top-p 0.8 \
--top-k 20 \
--max-tokens 64 \\\n --max-model-len 4096
```
提供机构：
davanstrien
