RYDE-WORK/MiniCPM
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/MiniCPM.git synced 2026-02-05 14:43:30 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

增加了readme中模型量化的导航以及示例

Browse Source
This commit is contained in:
刘丹 2024-06-25 11:50:53 +08:00
parent e53c77c7e8
commit e65930db1c
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -49,6 +49,7 @@ MiniCPM 是面壁智能与清华大学自然语言处理实验室共同开源的
- [更新日志](#0) - [更新日志](#0)
- [模型下载](#1) - [模型下载](#1)
- [快速上手](#2) - [快速上手](#2)
- [模型量化](#quantize)
- [开源社区](#community) - [开源社区](#community)
- [评测结果](#3) - [评测结果](#3)
- [手机部署](#4) - [手机部署](#4)
@ -258,7 +259,9 @@ print(model.response("<用户>山东省最高的山是哪座山, 它比黄山高
```shell ```shell
python -m mlx_lm.generate --model mlx-community/MiniCPM-2B-sft-bf16-llama-format-mlx --prompt "hello, tell me a joke." --trust-remote-code python -m mlx_lm.generate --model mlx-community/MiniCPM-2B-sft-bf16-llama-format-mlx --prompt "hello, tell me a joke." --trust-remote-code
``` ```
<p id="community"></p>
## 模型量化
**gptq量化** **gptq量化**
1. 首先git获取[minicpm_gptqd代码](https://github.com/LDLINGLINGLING/AutoGPTQ/tree/minicpm_gptq) 1. 首先git获取[minicpm_gptqd代码](https://github.com/LDLINGLINGLING/AutoGPTQ/tree/minicpm_gptq)
2. 进入minicpm_gptqd主目录./AutoGPTQ，命令行输入： 2. 进入minicpm_gptqd主目录./AutoGPTQ，命令行输入：