Rocketknight1 HF staff commited on
Commit
460ee72
1 Parent(s): 7f5b217

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -53,9 +53,10 @@ Each image captures a different scene, from a close-up of a dog to expansive nat
53
  """
54
  ```
55
 
56
- You can also use a chat template to format your chat history for Pixtral. Here's an example - note how you can interleave text and multiple images in the same message!
57
- Make sure that the `images` argument to the `processor` contains the images in the order that they appear in the chat, so that the model understands where
58
- each image is supposed to go.
 
59
 
60
  ```python
61
  from PIL import Image
@@ -105,6 +106,6 @@ If you're asking whether the dog can "live here," referring to the snowy landsca
105
  Would you like more information on any specific aspect?
106
  ```
107
 
108
- Note that while it may appear that spacing in the input is disrupted, this is caused by us skipping special tokens for display, and actually "Can this animal" and "live here" are
109
  correctly separated by image tokens. Try decoding with special tokens included to see exactly what the model sees!
110
 
 
53
  """
54
  ```
55
 
56
+ You can also use a chat template to format your chat history for Pixtral. Make sure that the `images` argument to the `processor` contains the images in the order
57
+ that they appear in the chat, so that the model understands where each image is supposed to go.
58
+
59
+ Here's an example with text and multiple images interleaved in the same message:
60
 
61
  ```python
62
  from PIL import Image
 
106
  Would you like more information on any specific aspect?
107
  ```
108
 
109
+ While it may appear that spacing in the input is disrupted, this is caused by us skipping special tokens for display, and actually "Can this animal" and "live here" are
110
  correctly separated by image tokens. Try decoding with special tokens included to see exactly what the model sees!
111