bokesyo commited on
Commit
7923606
1 Parent(s): 1aa4eca

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -13,12 +13,11 @@ With MiniCPM-Visual-Embedding, it is possible to directly build knowledge base w
13
 
14
  [Github Repo](https://github.com/bokesyo/minicpm-visual-embedding)
15
 
16
-
17
  ![Memex Archtechture](images/memex.png)
18
 
19
  # News
20
 
21
- - 2024-06-27: We released our first visual embedding model minicpm-visual-embedding-v0.1 on [huggingface](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0).
22
 
23
  - 2024-05-08: We [committed](https://github.com/bokesyo/minicpm-visual-embedding) our training code (full-parameter tuning with GradCache and DeepSpeed, supports large batch size across multiple GPUs with zero-stage1) and eval code.
24
 
@@ -33,6 +32,7 @@ torch==2.1.2
33
  torchvision==0.16.2
34
  transformers==4.36.0
35
  sentencepiece==0.1.99
 
36
  ```
37
 
38
  First you are suggested to git clone this huggingface repo or download repo with `huggingface_cli`.
 
13
 
14
  [Github Repo](https://github.com/bokesyo/minicpm-visual-embedding)
15
 
 
16
  ![Memex Archtechture](images/memex.png)
17
 
18
  # News
19
 
20
+ - 2024-06-27: We released our first visual embedding model checkpoint minicpm-visual-embedding-v0 on [huggingface](https://huggingface.co/RhapsodyAI/minicpm-visual-embedding-v0).
21
 
22
  - 2024-05-08: We [committed](https://github.com/bokesyo/minicpm-visual-embedding) our training code (full-parameter tuning with GradCache and DeepSpeed, supports large batch size across multiple GPUs with zero-stage1) and eval code.
23
 
 
32
  torchvision==0.16.2
33
  transformers==4.36.0
34
  sentencepiece==0.1.99
35
+ numpy==1.26.0
36
  ```
37
 
38
  First you are suggested to git clone this huggingface repo or download repo with `huggingface_cli`.