Files
ModelHub XC 12653872a5 初始化项目,由ModelHub XC社区提供模型
Model: marcelone/Hunyuan-7B-Instruct-GGUF
Source: Original Platform
2026-10-17 03:08:17 +08:00

52 lines
868 B
Markdown

---
license: other
license_name: tencent-hunyuan
license_link: https://github.com/Tencent-Hunyuan/Hunyuan-7B/blob/main/LICENSE.txt
base_model: tencent/Hunyuan-7B-Instruct
base_model_relation: quantized
tags:
- imatrix
- hunyuan_v1_dense
language:
- zh
- en
- ja
- es
- pt
- fr
- ko
pipeline_tag: text-generation
---
<table>
<thead>
<tr>
<th colspan="9">Output + Embedding</th>
</tr>
<tr>
<th>2-bit</th>
<th>3-bit</th>
<th>4-bit</th>
<th>5-bit</th>
<th>6-bit</th>
<th>8-bit</th>
<th>16-bit</th>
<th>32-bit</th>
</tr>
</thead>
<tbody>
<tr>
<td>AXL</td>
<td>BXL</td>
<td>CXL</td>
<td>DXL</td>
<td>EXL</td>
<td>FXL</td>
<td>GXL</td>
<td>HXL</td>
</tr>
</tbody>
</table>
**Notes**
* This model performs poorly on correcting German texts.