Instructions to use maciek-pioro/Mixtral-8x7B-v0.1-pl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maciek-pioro/Mixtral-8x7B-v0.1-pl with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="maciek-pioro/Mixtral-8x7B-v0.1-pl")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("maciek-pioro/Mixtral-8x7B-v0.1-pl") model = AutoModel.from_pretrained("maciek-pioro/Mixtral-8x7B-v0.1-pl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,6 +27,8 @@ Our codebase is based on [the Focused Transformer repo](https://github.com/CStan
|
|
| 27 |
|
| 28 |
Thanks to Konrad Staniszewski, Bartłomiej Cupiał and Piotr Miłoś, who have contributed greatly to the creation of this model.
|
| 29 |
|
|
|
|
|
|
|
| 30 |
## Example outputs
|
| 31 |
|
| 32 |
(prompts are in bold)
|
|
|
|
| 27 |
|
| 28 |
Thanks to Konrad Staniszewski, Bartłomiej Cupiał and Piotr Miłoś, who have contributed greatly to the creation of this model.
|
| 29 |
|
| 30 |
+
To release this model, we also used the Entropy cluster (hosted at the Faculty of Mathematics, Informatics and Mechanics of the University of Warsaw) funded by NVIDIA, Intel, the Polish National Science Center grant 2022/45/N/ST6/02222, and ERC Starting Grant TOTAL.
|
| 31 |
+
|
| 32 |
## Example outputs
|
| 33 |
|
| 34 |
(prompts are in bold)
|