Add library_name, pipeline tag and paper link

#5
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +7 -4
README.md CHANGED
@@ -6,18 +6,21 @@ tags:
6
  - MiniCPM
7
  - ModelBest
8
  - THUNLP
 
 
9
  ---
10
 
11
-
12
  <div align="center">
13
  <h1>
14
  MiniCPM
15
  </h1>
16
  </div>
17
 
 
 
18
  <p align="center">
19
  <a href="https://shengdinghu.notion.site/MiniCPM-c805a17c5c8046398914e47f0542095a?pvs=4" target="_blank">MiniCPM 技术报告</a><a href="https://shengdinghu.notion.site/MiniCPM-Unveiling-the-Potential-of-End-side-Large-Language-Models-d4d3a8c426424654a4e80e42a711cb20?pvs=4" target="_blank"> Technical Report</a> |
20
- <a href="https://github.com/OpenBMB/OmniLMM/" target="_blank">OmniLMM 多模态模型 Multi-modal Model</a> |
21
  <a href="https://luca.cn/" target="_blank">CPM-C 千亿模型试用 ~100B Model Trial </a>
22
  </p>
23
 
@@ -36,7 +39,7 @@ MiniCPM 是面壁与清华大学自然语言处理实验室共同开源的系列
36
  - 基于MLC-LLM、LLMFarm开发的MiniCPM手机端程序,**文本及多模态模型均可在手机端进行推理。**
37
 
38
 
39
- MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings.
40
 
41
  - MiniCPM has very close performance compared with Mistral-7B on open-sourced general benchmarks with better ability on Chinese, Mathmetics and Coding after SFT. The overall performance exceeds Llama2-13B, MPT-30B, Falcon-40B, etc.
42
  - After DPO, MiniCPM outperforms Llama2-70B-Chat, Vicuna-33B, Mistral-7B-Instruct-v0.1, Zephyr-7B-alpha, etc. on MTBench.
@@ -148,4 +151,4 @@ print(responds)
148
  booktitle={OpenBMB Blog},
149
  year={2024}
150
  }
151
- ```
 
6
  - MiniCPM
7
  - ModelBest
8
  - THUNLP
9
+ library_name: transformers
10
+ pipeline_tag: text-generation
11
  ---
12
 
 
13
  <div align="center">
14
  <h1>
15
  MiniCPM
16
  </h1>
17
  </div>
18
 
19
+ This repository contains the model of the paper [MiniCPM4: Ultra-Efficient LLMs on End Devices](https://huggingface.co/papers/2506.07900).
20
+
21
  <p align="center">
22
  <a href="https://shengdinghu.notion.site/MiniCPM-c805a17c5c8046398914e47f0542095a?pvs=4" target="_blank">MiniCPM 技术报告</a><a href="https://shengdinghu.notion.site/MiniCPM-Unveiling-the-Potential-of-End-side-Large-Language-Models-d4d3a8c426424654a4e80e42a711cb20?pvs=4" target="_blank"> Technical Report</a> |
23
+ <a href="https://github.com/OpenBMB/OmniLMM/\" target="_blank">OmniLMM 多模态模型 Multi-modal Model</a> |
24
  <a href="https://luca.cn/" target="_blank">CPM-C 千亿模型试用 ~100B Model Trial </a>
25
  </p>
26
 
 
39
  - 基于MLC-LLM、LLMFarm开发的MiniCPM手机端程序,**文本及多模态模型均可在手机端进行推理。**
40
 
41
 
42
+ MiniCPM is an End-Size LLM developed by ModelBest Inc. and TsinghuaNLP, with only 2.4B parameters excluding embeddings
43
 
44
  - MiniCPM has very close performance compared with Mistral-7B on open-sourced general benchmarks with better ability on Chinese, Mathmetics and Coding after SFT. The overall performance exceeds Llama2-13B, MPT-30B, Falcon-40B, etc.
45
  - After DPO, MiniCPM outperforms Llama2-70B-Chat, Vicuna-33B, Mistral-7B-Instruct-v0.1, Zephyr-7B-alpha, etc. on MTBench.
 
151
  booktitle={OpenBMB Blog},
152
  year={2024}
153
  }
154
+ ```