BramVanroy commited on
Commit
c4ebe02
1 Parent(s): fd0f283

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -8
README.md CHANGED
@@ -37,15 +37,9 @@ language:
37
  </p>
38
  </blockquote>
39
 
40
- # fietje-2b-sft
41
 
42
- This model is a fine-tuned version of [BramVanroy/fietje-2b](https://huggingface.co/BramVanroy/fietje-2b) on the generator dataset.
43
- It achieves the following results on the evaluation set:
44
- - Loss: 0.8818
45
-
46
- ## Model description
47
-
48
- More information needed
49
 
50
  ## Intended uses & limitations
51
 
 
37
  </p>
38
  </blockquote>
39
 
40
+ Fietje is an adapated version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2), tailored to Dutch text generation by training on 28B tokens. It is small and efficient with a size of 2.7 billion parameters while performing almost on par with more powerful Dutch LLMs of twice its size like [GEITje 7B Ultra](https://huggingface.co/BramVanroy/GEITje-7B-ultra).
41
 
42
+ A thorough description of the creation and evaluation of Fietje as well as usage examples is available in [this Github repository](https://github.com/BramVanroy/fietje).
 
 
 
 
 
 
43
 
44
  ## Intended uses & limitations
45