Hugging Face's logo

openbmb
/
MiniCPM-2B-128k

Text Generation
Transformers
PyTorch
Chinese
English
MiniCPM
ModelBest
THUNLP
conversational
custom_code
Model card Files Community
6
neoz commited on
Commit
6011acb
•
1 Parent(s): cc0a784

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -29,7 +29,7 @@ In comparison with the previous released [MiniCPM-2B](https://huggingface.co/ope
29
  - To facilitate community developers, the model has updated the <user>{}<AI> directive template to chatml format (user\n{}\nassistant\n) during alignment, which also aids users in deploying and using the vllm openai compatible server mode.
30
  - Due to the parallel mechanism requirement, removed tie_embedding and expanded the vocabulary to 127660.
31
 
32
- For more details, please refer to the [GitHub repo](https://github.com/OpenBMB/MiniCPM) and [Blog]().
33
 
34
 
35
  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端侧语言大模型，主体语言模型 [MiniCPM-2B](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) 仅有 24亿（2.4B）的非词嵌入参数量。
@@ -39,7 +39,7 @@ MiniCPM-2B-128k 是一次基于 [MiniCPM-2B](https://huggingface.co/openbmb/Mini
39
  - 为方便社区开发者使用，该模型在对齐时将 <用户>{}<AI> 指令模板更新为了 chatml 格式（<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n），这也有助于用户使用 vllm openai compatible server 模式部署和使用。
40
  - 由于并行机制需要,去除了 tie_embedding，并扩展词表到 127660。
41
 
42
- 更多细节请参考 [GitHub repo](https://github.com/OpenBMB/MiniCPM) 和 [Blog]()
43
 
44
  ## Evaluation Results 评测结果
45
 
 
29
  - To facilitate community developers, the model has updated the <user>{}<AI> directive template to chatml format (user\n{}\nassistant\n) during alignment, which also aids users in deploying and using the vllm openai compatible server mode.
30
  - Due to the parallel mechanism requirement, removed tie_embedding and expanded the vocabulary to 127660.
31
 
32
+ For more details, please refer to the [GitHub repo](https://github.com/OpenBMB/MiniCPM) and [Blog](https://openbmb.vercel.app/minicpm-2b-128k-en).
33
 
34
 
35
  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端侧语言大模型，主体语言模型 [MiniCPM-2B](https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16) 仅有 24亿（2.4B）的非词嵌入参数量。
 
39
  - 为方便社区开发者使用，该模型在对齐时将 <用户>{}<AI> 指令模板更新为了 chatml 格式（<|im_start|>user\n{}<|im_end|>\n<|im_start|>assistant\n），这也有助于用户使用 vllm openai compatible server 模式部署和使用。
40
  - 由于并行机制需要,去除了 tie_embedding，并扩展词表到 127660。
41
 
42
+ 更多细节请参考 [GitHub repo](https://github.com/OpenBMB/MiniCPM) 和 [Blog](https://openbmb.vercel.app/minicpm-2b-128k)
43
 
44
  ## Evaluation Results 评测结果
45