Ponimash commited on
Commit
a7eb61c
1 Parent(s): 9d60ea9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -20,7 +20,7 @@ library_name: transformers
20
 
21
 
22
  This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
23
- This is a fast and small model for solving the problem of determining the proximity between sentences, in the future we will reduce and speed it up. [Project](https://github.com/FractalGPT/ModelEmbedderDistilation)
24
 
25
  <!--- Describe your model here -->
26
 
@@ -66,9 +66,9 @@ cos(a, b)
66
  * The original weights was taken from [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2).
67
  * Training was conducted in two stages:
68
  1. In the first stage, the model was trained on Wikipedia texts (4 million texts) for three epochs.
69
- <img src="https://github.com/FractalGPT/ModelEmbedderDistilation/blob/main/DistilSBERT/Train/1_st_en.JPG?raw=true" width=700 />
70
  3. In the second stage, training was conducted on Wikipedia and dialog dataset for one epoch.
71
- <img src="https://github.com/FractalGPT/ModelEmbedderDistilation/blob/main/DistilSBERT/Train/2_st_en.JPG?raw=true" width=700 />
72
 
73
  ## Full Model Architecture
74
  ```
 
20
 
21
 
22
  This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
23
+ This is a fast and small model for solving the problem of determining the proximity between sentences, in the future we will reduce and speed it up. [Project](https://github.com/FractalGPT/ModelEmbedderDistillation)
24
 
25
  <!--- Describe your model here -->
26
 
 
66
  * The original weights was taken from [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2).
67
  * Training was conducted in two stages:
68
  1. In the first stage, the model was trained on Wikipedia texts (4 million texts) for three epochs.
69
+ <img src="https://github.com/FractalGPT/ModelEmbedderDistillation/blob/main/DistilSBERT/Train/1_st_en.JPG?raw=true" width=700 />
70
  3. In the second stage, training was conducted on Wikipedia and dialog dataset for one epoch.
71
+ <img src="https://github.com/FractalGPT/ModelEmbedderDistillation/blob/main/DistilSBERT/Train/2_st_en.JPG?raw=true" width=700 />
72
 
73
  ## Full Model Architecture
74
  ```