docs: made suggested changes

docs/notebooks/image_to_image.ipynb

@@ -315,13 +315,13 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Before and After\n",
-        "We can directly compare the results of our fine-tuned model with a its zero-shot counterpart to getter a better idea of how finetuning affects the results of a search. While the differences between the two models may be subtle for some queries, the examples below show that the model after fine-tuning is able to better match images look similar (like the first query), as well as match images that represent the same (or similar) things, despite not looking similar (like the second query):\n",
+        "## Before and after\n",
+        "We can directly compare the results of our fine-tuned model with its zero-shot counterpart to get a better idea of how finetuning affects the results of a search. While the differences between the two models may be subtle for some queries, some of the examples the examples below (such as the the second example) show that the model after fine-tuning is able to better match similar images.\n",
         "\n",
         "```python\n",
         "import copy\n",
-        "from PIL import Image\n",
         "from io import BytesIO\n",
+        "from PIL import Image\n",
         "\n",
         "query_pt = copy.deepcopy(query_data)\n",
         "index_pt = copy.deepcopy(index_data)\n",

docs/notebooks/image_to_image.md

@@ -209,13 +209,13 @@ query.match(index_data, limit=10, metric='cosine')
 ```
 
 <!-- #region -->
-## Before and After
-We can directly compare the results of our fine-tuned model with a its zero-shot counterpart to getter a better idea of how finetuning affects the results of a search. While the differences between the two models may be subtle for some queries, the examples below show that the model after fine-tuning is able to better match images look similar (like the first query), as well as match images that represent the same (or similar) things, despite not looking similar (like the second query):
+## Before and after
+We can directly compare the results of our fine-tuned model with its zero-shot counterpart to get a better idea of how finetuning affects the results of a search. While the differences between the two models may be subtle for some queries, some of the examples the examples below (such as the the second example) show that the model after fine-tuning is able to better match similar images.
 
 ```python
 import copy
-from PIL import Image
 from io import BytesIO
+from PIL import Image
 
 query_pt = copy.deepcopy(query_data)
 index_pt = copy.deepcopy(index_data)

docs/notebooks/multilingual_text_to_image.ipynb

@@ -304,7 +304,7 @@
    "id": "38bc9069-0f0e-47c6-8560-bf77ad200774",
    "metadata": {},
    "source": [
-    "## Before and After\n",
+    "## Before and after\n",
     "We can directly compare the results of our fine-tuned model with an untrained multilingual clip model by displaying the matches each model has for the same query, while the differences between the results of the two models are quite subtle for some queries, the examples below clearly show that finetuning increses the quality of the search results:"
    ]
   },
@@ -323,12 +323,12 @@
     "ft_index = copy.deepcopy(index_data)\n",
     "\n",
     "zero_shot_text_encoder = build_model(\n",
-    "    name = 'xlm-roberta-base-ViT-B-32::laion5b_s13b_b90k',\n",
-    "    select_model = 'clip-text',\n",
+    "    name='xlm-roberta-base-ViT-B-32::laion5b_s13b_b90k',\n",
+    "    select_model='clip-text',\n",
     ")\n",
     "zero_shot_image_encoder = build_model(\n",
-    "    name = 'xlm-roberta-base-ViT-B-32::laion5b_s13b_b90k',\n",
-    "    select_model = 'clip-vision',\n",
+    "    name='xlm-roberta-base-ViT-B-32::laion5b_s13b_b90k',\n",
+    "    select_model='clip-vision',\n",
     ")\n",
     "\n",
     "finetuner.encode(model=zero_shot_text_encoder, data=pt_query)\n",

docs/notebooks/multilingual_text_to_image.md

@@ -191,7 +191,7 @@ please use `model = finetuner.get_model(artifact, is_onnx=True)`
 ```
 <!-- #endregion -->
 
-## Before and After
+## Before and after
 We can directly compare the results of our fine-tuned model with an untrained multilingual clip model by displaying the matches each model has for the same query, while the differences between the results of the two models are quite subtle for some queries, the examples below clearly show that finetuning increses the quality of the search results:
 
 <!-- #region -->
@@ -205,12 +205,12 @@ ft_query = copy.deepcopy(query_data)
 ft_index = copy.deepcopy(index_data)
 
 zero_shot_text_encoder = build_model(
-    name = 'xlm-roberta-base-ViT-B-32::laion5b_s13b_b90k',
-    select_model = 'clip-text',
+    name='xlm-roberta-base-ViT-B-32::laion5b_s13b_b90k',
+    select_model='clip-text',
 )
 zero_shot_image_encoder = build_model(
-    name = 'xlm-roberta-base-ViT-B-32::laion5b_s13b_b90k',
-    select_model = 'clip-vision',
+    name='xlm-roberta-base-ViT-B-32::laion5b_s13b_b90k',
+    select_model='clip-vision',
 )
 
 finetuner.encode(model=zero_shot_text_encoder, data=pt_query)

docs/notebooks/text_to_image.ipynb

@@ -305,8 +305,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Before and After\n",
-        "We can directly compare the results of our fine-tuned model with an untrained clip model by displaying the matches each model has for the same query, while the differences between the results of the two models are quite subtle for some queries, the examples below clearly show that finetuning increses the quality of the search results:"
+        "## Before and after\n",
+        "We can directly compare the results of our fine-tuned model with a pre-trained clip model by displaying the matches each model has for the same query. While the differences between the results of the two models are quite subtle for some queries, the examples below clearly show that finetuning increases the quality of the search results:"
       ]
     },
     {
@@ -324,12 +324,12 @@
         "ft_index = copy.deepcopy(index_data)\n",
         "\n",
         "zero_shot_text_encoder = build_model(\n",
-        "    name = 'openai/clip-vit-base-patch32',\n",
-        "    select_model = 'clip-text',\n",
+        "    name='openai/clip-vit-base-patch32',\n",
+        "    select_model='clip-text',\n",
         ")\n",
         "zero_shot_image_encoder = build_model(\n",
-        "    name = 'openai/clip-vit-base-patch32',\n",
-        "    select_model = 'clip-vision',\n",
+        "    name='openai/clip-vit-base-patch32',\n",
+        "    select_model='clip-vision',\n",
         ")\n",
         "\n",
         "finetuner.encode(model=zero_shot_text_encoder, data=pt_query)\n",

docs/notebooks/text_to_image.md

@@ -206,8 +206,8 @@ please use `model = finetuner.get_model(artifact, is_onnx=True)`
 ```
 <!-- #endregion -->
 
-## Before and After
-We can directly compare the results of our fine-tuned model with an untrained clip model by displaying the matches each model has for the same query, while the differences between the results of the two models are quite subtle for some queries, the examples below clearly show that finetuning increses the quality of the search results:
+## Before and after
+We can directly compare the results of our fine-tuned model with a pre-trained clip model by displaying the matches each model has for the same query. While the differences between the results of the two models are quite subtle for some queries, the examples below clearly show that finetuning increases the quality of the search results:
 
 <!-- #region -->
 ```python
@@ -221,12 +221,12 @@ ft_query = copy.deepcopy(query_data)
 ft_index = copy.deepcopy(index_data)
 
 zero_shot_text_encoder = build_model(
-    name = 'openai/clip-vit-base-patch32',
-    select_model = 'clip-text',
+    name='openai/clip-vit-base-patch32',
+    select_model='clip-text',
 )
 zero_shot_image_encoder = build_model(
-    name = 'openai/clip-vit-base-patch32',
-    select_model = 'clip-vision',
+    name='openai/clip-vit-base-patch32',
+    select_model='clip-vision',
 )
 
 finetuner.encode(model=zero_shot_text_encoder, data=pt_query)

docs/notebooks/text_to_text.ipynb

@@ -338,8 +338,8 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Before and After\n",
-        "We can directly compare the results of our fine-tuned model with a its zero-shot counterpart to getter a better idea of how finetuning affects the results of a search. While the zero-shot model is able to produce results that are very similar to the initial query, it is common for the topic of the question to change, with the structure staying the same. After fine-tuning, the returned questions are consistently relevant to the initial query, even in cases where the structure of the sentence is different.\n",
+        "## Before and after\n",
+        "We can directly compare the results of our fine-tuned model with its zero-shot counterpart to get a better idea of how finetuning affects the results of a search. While the zero-shot model is able to produce results that are very similar to the initial query, it is common for the topic of the question to change, with the structure staying the same. After fine-tuning, the returned questions are consistently relevant to the initial query, even in cases where the structure of the sentence is different.\n",
         "\n",
         "```python\n",
         "import copy\n",

docs/notebooks/text_to_text.md

@@ -227,8 +227,8 @@ query.match(index_data, limit=10, metric='cosine')
 ```
 
 <!-- #region -->
-## Before and After
-We can directly compare the results of our fine-tuned model with a its zero-shot counterpart to getter a better idea of how finetuning affects the results of a search. While the zero-shot model is able to produce results that are very similar to the initial query, it is common for the topic of the question to change, with the structure staying the same. After fine-tuning, the returned questions are consistently relevant to the initial query, even in cases where the structure of the sentence is different.
+## Before and after
+We can directly compare the results of our fine-tuned model with its zero-shot counterpart to get a better idea of how finetuning affects the results of a search. While the zero-shot model is able to produce results that are very similar to the initial query, it is common for the topic of the question to change, with the structure staying the same. After fine-tuning, the returned questions are consistently relevant to the initial query, even in cases where the structure of the sentence is different.
 
 ```python
 import copy