Instructions to use winninghealth/WiNGPT-Babel-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use winninghealth/WiNGPT-Babel-2 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="winninghealth/WiNGPT-Babel-2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("winninghealth/WiNGPT-Babel-2") model = AutoModelForCausalLM.from_pretrained("winninghealth/WiNGPT-Babel-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -124,7 +124,7 @@ The performance improvements in WiNGPT-Babel-2 are attributed to a continuous, d
|
|
| 124 |
<tr>
|
| 125 |
<td align="center">WiNGPT-Babel-2-AWQ</td>
|
| 126 |
<td align="center">36.43</td>
|
| 127 |
-
<td align="center">
|
| 128 |
</tr>
|
| 129 |
</tbody>
|
| 130 |
</table>
|
|
|
|
| 124 |
<tr>
|
| 125 |
<td align="center">WiNGPT-Babel-2-AWQ</td>
|
| 126 |
<td align="center">36.43</td>
|
| 127 |
+
<td align="center">24.45</td>
|
| 128 |
</tr>
|
| 129 |
</tbody>
|
| 130 |
</table>
|