Skip to content

Commit

Permalink
Merge pull request nebuly-ai#195 from eltociear/patch-2
Browse files Browse the repository at this point in the history 
Update huggingface/Readme.md
  • Loading branch information
@diegofiori
diegofiori authored Mar 1, 2023
2 parents 626e17f + 9bb2455 commit e55d9ec
Showing 1 changed file with 9 additions and 9 deletions.
18 changes: 9 additions & 9 deletions notebooks/speedster/huggingface/Readme.md
View file
Original file line number Diff line number Diff line change
@@ -1,10 +1,10 @@
# **HuggingFace Optimization**
# **Hugging Face Optimization**

This section contains all the available notebooks that show how to leverage Speedster to optimize HuggingFace models.
This section contains all the available notebooks that show how to leverage Speedster to optimize Hugging Face models.

HuggingFace hosts models that can use either PyTorch or TensorFlow as backend. Both the backends are supported by Speedster.
Hugging Face hosts models that can use either PyTorch or TensorFlow as backend. Both the backends are supported by Speedster.

## HuggingFace API quick view:
## Hugging Face API quick view:

``` python
from speedster import optimize_model
Expand Down Expand Up @@ -53,8 +53,8 @@ res = optimized_model(**input_dict)
## Notebooks:
| Notebook | Description | |
|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [Accelerate HuggingFace PyTorch GPT2](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_GPT2_with_Speedster.ipynb) | Show how to optimize with Speedster the GPT2 model from Huggingface with PyTorch backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_GPT2_with_Speedster.ipynb) |
| [Accelerate HuggingFace PyTorch BERT](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_BERT_with_Speedster.ipynb) | Show how to optimize with Speedster the BERT model from Huggingface with PyTorch backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_BERT_with_Speedster.ipynb) |
| [Accelerate HuggingFace PyTorch DistilBERT](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_DistilBERT_with_Speedster.ipynb) | Show how to optimize with Speedster the DistilBERT model from Huggingface with PyTorch backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_DistilBERT_with_Speedster.ipynb) | |
| [Accelerate HuggingFace TensorFlow BERT](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_TensorFlow_BERT_with_Speedster.ipynb) | Show how to optimize with Speedster the BERT model from Huggingface with TensorFlow backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_TensorFlow_BERT_with_Speedster.ipynb) |
| [Accelerate HuggingFace PyTorch T5](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_T5_with_Speedster.ipynb) | Show how to optimize with Speedster the T5 model from Huggingface with PyTorch backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_T5_with_Speedster.ipynb) |
| [Accelerate Hugging Face PyTorch GPT2](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_GPT2_with_Speedster.ipynb) | Show how to optimize with Speedster the GPT2 model from Hugging Face with PyTorch backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_GPT2_with_Speedster.ipynb) |
| [Accelerate Hugging Face PyTorch BERT](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_BERT_with_Speedster.ipynb) | Show how to optimize with Speedster the BERT model from Hugging Face with PyTorch backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_BERT_with_Speedster.ipynb) |
| [Accelerate Hugging Face PyTorch DistilBERT](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_DistilBERT_with_Speedster.ipynb) | Show how to optimize with Speedster the DistilBERT model from Hugging Face with PyTorch backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_DistilBERT_with_Speedster.ipynb) | |
| [Accelerate Hugging Face TensorFlow BERT](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_TensorFlow_BERT_with_Speedster.ipynb) | Show how to optimize with Speedster the BERT model from Hugging Face with TensorFlow backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_TensorFlow_BERT_with_Speedster.ipynb) |
| [Accelerate Hugging Face PyTorch T5](https://github.com/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_T5_with_Speedster.ipynb) | Show how to optimize with Speedster the T5 model from Hugging Face with PyTorch backend. | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nebuly-ai/nebullvm/blob/main/notebooks/speedster/huggingface/Accelerate_Hugging_Face_PyTorch_T5_with_Speedster.ipynb) |

0 comments on commit e55d9ec

Please sign in to comment.