luodian commited on
Commit
33caa26
1 Parent(s): bac706e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -2,6 +2,12 @@
2
  license: mit
3
  ---
4
 
 
 
 
 
 
 
5
  ```python
6
  from flamingo.modeling_flamingo import FlamingoForConditionalGeneration
7
  flamingo_model = FlamingoForConditionalGeneration.from_pretrained("luodian/Flamingo-Llama2-Chat7B-CC3M", device_map=auto)
 
2
  license: mit
3
  ---
4
 
5
+ **TLDR**: We trained a Flamingo with Llama2-Chat7B as LLM on CC3M in less than 5 hours using just 4 A100s.
6
+
7
+ The model showed promising zero-shot captioning skills. High-quality captioning data really helps fast alignment.
8
+
9
+ You could test it via following code. Be sure to visit [Otter](https://github.com/Luodian/Otter) to get necessary Flamingo/Otter models.
10
+
11
  ```python
12
  from flamingo.modeling_flamingo import FlamingoForConditionalGeneration
13
  flamingo_model = FlamingoForConditionalGeneration.from_pretrained("luodian/Flamingo-Llama2-Chat7B-CC3M", device_map=auto)