RYDE-WORK/MiniCPM
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/MiniCPM.git synced 2026-02-05 22:53:34 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

add community session

Browse Source
This commit is contained in:
shengdinghu 2024-02-09 14:05:50 +07:00
parent 855434ef75
commit f2a8c95990
2 changed files with 21 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
README-en.md
View File

@ -44,6 +44,7 @@ We release all model parameters for research and limited commercial use. In futu
- [Updates](#0) - [Updates](#0)
- [Downloading](#1) - [Downloading](#1)
- [Quick Start](#2) - [Quick Start](#2)
- [Community](#community)
- [Benchmark](#3) - [Benchmark](#3)
- [Deployment on Mobile Phones](#4) - [Deployment on Mobile Phones](#4)
- [Demo & API](#5) - [Demo & API](#5)
@ -55,6 +56,7 @@ We release all model parameters for research and limited commercial use. In futu
<p id="0"></p> <p id="0"></p>
## Update Log ## Update Log
- 2024/02/09 We have included a [Community](#community) section in the README to encourage support for MiniCPM from the open-source community.
- 2024/02/08 We updated the [llama-format model weights](#llamaformat), which can be loaded into LlamaModel directly. We also supporting llama.cpp and ollama, making it more convenient for everyone to use our model quickly. - 2024/02/08 We updated the [llama-format model weights](#llamaformat), which can be loaded into LlamaModel directly. We also supporting llama.cpp and ollama, making it more convenient for everyone to use our model quickly.
- 2024/02/01 Initial release. - 2024/02/01 Initial release.
@ -202,6 +204,14 @@ ollama run minicpm
``` ```
(Note: We have noticed that this quantized model has noticable performance decrease and are trying to fix it) (Note: We have noticed that this quantized model has noticable performance decrease and are trying to fix it)
<p id="Community"></p>
## Community
- [ChatLLM](https://github.com/foldl/chatllm.cpp) :[Run MiniCPM on CPU](https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16/discussions/2#65c59c4f27b8c11e43fc8796)
<p id="3"></p> <p id="3"></p>
## Evaluation results ## Evaluation results

11
README.md
View File

@ -45,6 +45,7 @@ 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)
- [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)
- [Demo & API 部署](#5) - [Demo & API 部署](#5)
@ -56,6 +57,7 @@ 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
<p id="0"></p> <p id="0"></p>
## 更新日志 ## 更新日志
- 2024/02/09 我们在readme里加入了一个[开源社区](#community)章节，用来收集开源社区对MiniCPM的支持案例。
- 2024/02/08 我们更新了[llama-format的模型权重](#llamaformat)，支持了llama.cpp调用和ollama调用，方便大家更加快捷地使用我们的模型。 - 2024/02/08 我们更新了[llama-format的模型权重](#llamaformat)，支持了llama.cpp调用和ollama调用，方便大家更加快捷地使用我们的模型。
- 2024/02/01 初始发布。 - 2024/02/01 初始发布。
@ -212,6 +214,15 @@ ollama run minicpm
``` ```
（注：我们注意到这个量化后的模型性能有较大损失，正在尝试解决） （注：我们注意到这个量化后的模型性能有较大损失，正在尝试解决）
<p id="community"></p>
## 开源社区
- [ChatLLM框架](https://github.com/foldl/chatllm.cpp):[在CPU上跑MiniCPM](https://huggingface.co/openbmb/MiniCPM-2B-dpo-bf16/discussions/2#65c59c4f27b8c11e43fc8796)
<p id="3"></p> <p id="3"></p>
## 评测结果 ## 评测结果