Spaces:
Sleeping
Sleeping
osanseviero
commited on
Commit
•
4d21c15
1
Parent(s):
c93a9b2
Update Mistral_7B.ipynb
Browse files- Mistral_7B.ipynb +1 -1
Mistral_7B.ipynb
CHANGED
@@ -38,7 +38,7 @@
|
|
38 |
"In this Colab, we'll experiment with the Mistral model using an API. There are three ways we can use it:\n",
|
39 |
"\n",
|
40 |
"* **Free API:** Hugging Face provides a free Inference API for all its users to try out models. This API is rate limited but is great for quick experiments.\n",
|
41 |
-
"* **PRO API:** Hugging Face provides an open API for all its PRO users. Subscribing to the Pro Inference API costs $9/month and allows you to experiment with many large models, such as Llama 2 and SDXL. Read more about it [here](https://huggingface.co/blog/inference-pro).\n",
|
42 |
"* **Inference Endpoints:** For enterprise and production-ready cases. You can deploy it with 1 click [here](https://ui.endpoints.huggingface.co/catalog).\n",
|
43 |
"\n",
|
44 |
"This demo does not require GPU Colab, just CPU. You can grab your token at https://huggingface.co/settings/tokens.\n",
|
|
|
38 |
"In this Colab, we'll experiment with the Mistral model using an API. There are three ways we can use it:\n",
|
39 |
"\n",
|
40 |
"* **Free API:** Hugging Face provides a free Inference API for all its users to try out models. This API is rate limited but is great for quick experiments.\n",
|
41 |
+
"* **PRO and Enterprise API:** Hugging Face provides an open API for all its PRO users. Subscribing to the Pro Inference API costs $9/month and allows you to experiment with many large models, such as Llama 2 and SDXL. Read more about it [here](https://huggingface.co/blog/inference-pro).\n",
|
42 |
"* **Inference Endpoints:** For enterprise and production-ready cases. You can deploy it with 1 click [here](https://ui.endpoints.huggingface.co/catalog).\n",
|
43 |
"\n",
|
44 |
"This demo does not require GPU Colab, just CPU. You can grab your token at https://huggingface.co/settings/tokens.\n",
|