LearnItAnyway commited on
Commit
1e2a08e
1 Parent(s): 2b5db73

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -0
README.md CHANGED
@@ -1,3 +1,21 @@
1
  ---
2
  license: other
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: other
3
  ---
4
+ # Model Card for llava-polyglot-ko-1.3b-hf
5
+
6
+ ## Model Description
7
+
8
+ ` llava-polyglot-ko-1.3b-hf ` is a model based on polyglot-ko-13b.
9
+ We use llava for the vision question answering.
10
+ You can see [‘demo.py’]( https://github.com/LearnItAnyway/llava_gpt_neox/blob/main/demo.py) and [‘llava_gpt_neox.py’]( https://github.com/LearnItAnyway/llava_gpt_neox/blob/main/llava_gpt_neox.py).
11
+ Currently, the model has been trained on small vision question answer dataset (approx, 10k) with 1.3b (small) model.
12
+
13
+ ## TODO
14
+ - Multi-turn chat based on the image
15
+ - Larger LLM
16
+ - More pretraining on for the vision-text adapter
17
+
18
+ ## References
19
+ - [`LLaVA`](https://github.com/haotian-liu/LLaVA)
20
+ - [`polyglot korean`](https://huggingface.co/EleutherAI/polyglot-ko-1.3b)
21
+