VictorSanh commited on
Commit
84bc60f
1 Parent(s): 335ef98

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -60,8 +60,8 @@ We release under the Apache 2.0 license 2 checkpoints:
60
  For optimal results, we recommend fine-tuning `idefics2-8b` on one's specific use-case and data. In fact, the instruction-fine-tuned model (`idefics2-8b`) is significantly better at following instructions from users and thus should be preferred when using the models out-of-the-box or as a starting point for fine-tuning.
61
 
62
  As a starting point, we provide fine-tuning codes that can be adapted for one's particular scenario:
63
- <!-- - With the [TRL library](https://github.com/huggingface/trl): TODO -->
64
- - With the [Hugging Face Trainer](https://huggingface.co/docs/transformers/main/en/main_classes/trainer#api-reference%20][%20transformers.Trainer): [Tutorial notebook](https://colab.research.google.com/drive/1rm3AGquGEYXfeeizE40bbDtcWh5S4Nlq?usp=sharing)
65
 
66
 
67
  # Technical summary
 
60
  For optimal results, we recommend fine-tuning `idefics2-8b` on one's specific use-case and data. In fact, the instruction-fine-tuned model (`idefics2-8b`) is significantly better at following instructions from users and thus should be preferred when using the models out-of-the-box or as a starting point for fine-tuning.
61
 
62
  As a starting point, we provide fine-tuning codes that can be adapted for one's particular scenario:
63
+ - With the [TRL library](https://github.com/huggingface/trl): [Script](https://gist.github.com/edbeeching/228652fc6c2b29a1641be5a5778223cb)
64
+ - With the [Hugging Face Trainer](https://huggingface.co/docs/transformers/main/en/main_classes/trainer#api-reference%20][%20transformers.Trainer): [Tutorial notebook](https://colab.research.google.com/drive/1NtcTgRbSBKN7pYD3Vdx1j9m8pt3fhFDB?usp=sharing)
65
 
66
 
67
  # Technical summary