Hugging Face's logo

Ba2han
/
TinyLlama-Turkish-QLora-0.25

Turkish
Model card Files Community
Ba2han commited on
Commit
7b4af44
•
1 Parent(s): c7fbc53

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -6,9 +6,11 @@ language:
6
  - tr
7
  ---
8
 
 
 
9
  This QLoRA was trained for 0.25 epochs on TinyLlama 1.1B with Merve's Turkish_instructions dataset. It aims to take advantage of TinyLlama's huge token count.
10
 
11
- It is exceptionally bad, but it can consistently produce meaningful words and rarely form coherent sentences in Turkish.
12
 
13
  You can use the default template for TinyLlama.
14
 
 
6
  - tr
7
  ---
8
 
9
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6324eabf05bd8a54c6eb1650/2tIft9E7Ef2XU97X_zjfE.png)
10
+
11
  This QLoRA was trained for 0.25 epochs on TinyLlama 1.1B with Merve's Turkish_instructions dataset. It aims to take advantage of TinyLlama's huge token count.
12
 
13
+ It is exceptionally bad (due to low amount of training), but it can consistently produce meaningful words and rarely form coherent sentences in Turkish.
14
 
15
  You can use the default template for TinyLlama.
16