loubnabnl HF staff commited on
Commit
ce77f8f
β€’
1 Parent(s): 22c60ae

update html

Browse files
Files changed (1) hide show
  1. architectures/codeparrot.txt +2 -0
architectures/codeparrot.txt CHANGED
@@ -1,4 +1,5 @@
1
  [CodeParrot](https://huggingface.co/lvwerra/codeparrot) uses GPT-2 architecture with BPE tokenizer trained on Python code from the training split of the data, and a context length of 1024. We released this model as an educational tool for training large language models from scratch on code, with detailed tutorials and descriptions of the training process. It makes use of πŸ€— [`accelerate`](https://huggingface.co/docs/accelerate/index) for distributed training and mixed precision. See this [blog](https://huggingface.co/blog/codeparrot) and [repo](https://github.com/huggingface/transformers/tree/main/examples/research_projects/codeparrot) for more details.
 
2
  <div align="center">
3
 
4
  |Model | # parameters |
@@ -8,6 +9,7 @@
8
 
9
  </div>
10
 
 
11
  You can load the model and tokenizer directly from πŸ€— [`transformers`](https://huggingface.co/docs/transformers/index):
12
 
13
  ```python
 
1
  [CodeParrot](https://huggingface.co/lvwerra/codeparrot) uses GPT-2 architecture with BPE tokenizer trained on Python code from the training split of the data, and a context length of 1024. We released this model as an educational tool for training large language models from scratch on code, with detailed tutorials and descriptions of the training process. It makes use of πŸ€— [`accelerate`](https://huggingface.co/docs/accelerate/index) for distributed training and mixed precision. See this [blog](https://huggingface.co/blog/codeparrot) and [repo](https://github.com/huggingface/transformers/tree/main/examples/research_projects/codeparrot) for more details.
2
+
3
  <div align="center">
4
 
5
  |Model | # parameters |
 
9
 
10
  </div>
11
 
12
+
13
  You can load the model and tokenizer directly from πŸ€— [`transformers`](https://huggingface.co/docs/transformers/index):
14
 
15
  ```python