hyx21 commited on
Commit
98ea6c0
1 Parent(s): 3e5386d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -6
README.md CHANGED
@@ -16,7 +16,7 @@ tags:
16
  </div>
17
 
18
  <p align="center">
19
- <a href="XXXX" target="_blank">MiniCPM 技术报告 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>
@@ -51,9 +51,18 @@ We release all model parameters for research and limited commercial use. We also
51
  - The INT4 quantized version **MiniCPM-2B-SFT/DPO-Int4** based on MiniCPM-2B-SFT/DPO
52
  - Mobile phone application based on MLC-LLM and LLMFarm. Both language model and multimodel model can conduct inference on smartphones.
53
 
 
54
 
 
55
 
56
- ### 局限性 Limitations:
 
 
 
 
 
 
 
57
 
58
  - 受限于模型规模,模型可能出现幻觉性问题。其中由于DPO模型生成的回复内容更长,更容易出现幻觉。我们也将持续进行MiniCPM模型的迭代改进;
59
  - 为了保证在学术研究用途上模型的通用性,我们未对模型进行任何身份认同训练。同时由于我们用ShareGPT开源语料作为部分训练数据,模型可能会输出类似GPT系列模型的身份认同信息;
@@ -130,8 +139,8 @@ print(responds)
130
 
131
  ## 工作引用 Citation
132
 
133
- * 如果觉得MiniCPM有助于您的工作,请考虑引用下列[技术报告](todo)
134
- * Please cite our [techinical report]() if you find our work valuable.
135
 
136
  ```
137
  @inproceedings{minicpm2024,
@@ -140,5 +149,3 @@ print(responds)
140
  year={2024}
141
  }
142
  ```
143
-
144
-
 
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>
 
51
  - The INT4 quantized version **MiniCPM-2B-SFT/DPO-Int4** based on MiniCPM-2B-SFT/DPO
52
  - Mobile phone application based on MLC-LLM and LLMFarm. Both language model and multimodel model can conduct inference on smartphones.
53
 
54
+ ### 评测结果 Evaluation Results
55
 
56
+ 详细的评测结果位于[github仓库](https://github.com/OpenBMB/MiniCPM?tab=readme-ov-file#%E8%AF%84%E6%B5%8B%E7%BB%93%E6%9E%9C)
57
 
58
+ Detailed evaluation results are in [github repo](https://github.com/OpenBMB/MiniCPM/blob/main/README-en.md#evaluation-results)
59
+
60
+ 注意:我们发现使用Huggingface生成质量略差于vLLM,因此推荐使用vLLM进行测试。我们正在排查原因。
61
+
62
+ Notice: We discovered that the quality of Huggingface generation is slightly lower than vLLM, thus benchmarking using vLLM is recommended.
63
+ We are investigating the cause now.
64
+
65
+ ### 局限性 Limitations
66
 
67
  - 受限于模型规模,模型可能出现幻觉性问题。其中由于DPO模型生成的回复内容更长,更容易出现幻觉。我们也将持续进行MiniCPM模型的迭代改进;
68
  - 为了保证在学术研究用途上模型的通用性,我们未对模型进行任何身份认同训练。同时由于我们用ShareGPT开源语料作为部分训练数据,模型可能会输出类似GPT系列模型的身份认同信息;
 
139
 
140
  ## 工作引用 Citation
141
 
142
+ * 如果觉得MiniCPM有助于您的工作,请考虑引用下列[技术报告](https://shengdinghu.notion.site/MiniCPM-c805a17c5c8046398914e47f0542095a?pvs=4)
143
+ * Please cite our [techinical report](https://shengdinghu.notion.site/MiniCPM-Unveiling-the-Potential-of-End-side-Large-Language-Models-d4d3a8c426424654a4e80e42a711cb20?pvs=4) if you find our work valuable.
144
 
145
  ```
146
  @inproceedings{minicpm2024,
 
149
  year={2024}
150
  }
151
  ```