added info (#1675)

* added info

* Update 2024-10-01-jsl_medm_q8_v1_en.md

* Update 2024-10-01-jsl_meds_ner_q4_v2_en.md

* Update 2024-10-04-jsl_medm_q4_v1_en.md

* Update 2024-10-04-jsl_meds_ner_q16_v2_en.md

* Update 2024-10-04-jsl_meds_ner_q8_v2_en.md

* Update 2024-10-04-jsl_meds_ner_zs_q16_v1_en.md

* Update 2024-10-04-jsl_meds_ner_zs_q4_v1_en.md

* Update 2024-10-04-jsl_meds_ner_zs_q8_v1_en.md

* Update 2024-10-05-jsl_meds_q16_v1_en.md

* Update 2024-10-05-jsl_meds_q16_v2_en.md

* Update 2024-10-05-jsl_meds_q16_v3_en.md

* Update 2024-10-05-jsl_meds_q4_v1_en.md

* Update 2024-10-05-jsl_meds_q4_v2_en.md

* Update 2024-10-05-jsl_meds_q4_v3_en.md

* Update 2024-10-05-jsl_meds_q8_v1_en.md

* Update 2024-10-05-jsl_meds_q8_v2_en.md

* Update 2024-10-05-jsl_meds_q8_v3_en.md

* Update 2024-10-05-jsl_meds_rag_q16_v1_en.md

* Update 2024-10-05-jsl_meds_rag_q4_v1_en.md

* Update 2024-10-05-jsl_meds_rag_q8_v1_en.md

* Update 2024-10-06-jsl_medm_q4_v2_en.md

* Update 2024-10-06-jsl_medm_q4_v3_en.md

* Update 2024-10-06-jsl_medm_q8_v2_en.md

* Update 2024-10-08-jsl_medm_q16_v2_en.md

* Update 2024-10-08-jsl_medm_q8_v3_en.md

* Update 2024-10-15-jsl_medm_q16_v1_en.md

* Update 2024-10-15-jsl_medm_q16_v1_en.md

docs/_posts/akrztrk/2024-10-01-jsl_medm_q8_v1_en.md

@@ -19,7 +19,8 @@ use_language_switcher: "Python-Scala-Java"
 
 ## Description
 
-This LLM model is trained to perform Q&A, Summarization, RAG, and Chat
+This LLM model is trained to perform Q&A, Summarization, RAG, and Chat.
+
 
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
@@ -33,6 +34,7 @@ This LLM model is trained to perform Q&A, Summarization, RAG, and Chat
 
 <div class="tabs-box" markdown="1">
 {% include programmingLanguageSelectScalaPythonNLU.html %}
+
 ```python
 
 document_assembler = DocumentAssembler()\
@@ -220,7 +222,8 @@ KISUNLA is an amyloid beta-directed antibody indicated for the treatment of Alzh
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -272,4 +275,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | None     | 0.05         | 0.05                 | 0.06          |
 | Total    | 1.00         | 1.00                 | 1.00          |
 
-```
+```

docs/_posts/akrztrk/2024-10-01-jsl_meds_ner_q4_v2_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to extract and link entities in a document. Users needs to define an input schema as explained in the example section. Drug is defined as a list which tells the model that there could be multiple drugs in the document and it has to extract all of them. Each drug has properties like name and reaction. Since name is only one, it is a string, but there could be multiple reactions, hence it is a list. Similarly, users can define any schema for any type of entity.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -33,6 +34,7 @@ This LLM model is trained to extract and link entities in a document. Users need
 
 <div class="tabs-box" markdown="1">
 {% include programmingLanguageSelectScalaPythonNLU.html %}
+
 ```python
 
 document_assembler = DocumentAssembler()\
@@ -161,7 +163,8 @@ results.select("completions").show(truncate=False)
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -208,4 +211,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-04-jsl_medm_q4_v1_en.md

@@ -19,7 +19,8 @@ use_language_switcher: "Python-Scala-Java"
 
 ## Description
 
-This LLM model is trained to perform Q&A, Summarization, RAG, and Chat
+This LLM model is trained to perform Q&A, Summarization, RAG, and Chat.
+
 
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
@@ -220,7 +221,8 @@ KISUNLA is an amyloid beta-directed antibody indicated for the treatment of Alzh
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -272,4 +274,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | None     | 0.05         | 0.05                 | 0.06          |
 | Total    | 1.00         | 1.00                 | 1.00          |
 
-```
+```

docs/_posts/akrztrk/2024-10-04-jsl_meds_ner_q16_v2_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to extract and link entities in a document. Users needs to define an input schema as explained in the example section. Drug is defined as a list which tells the model that there could be multiple drugs in the document and it has to extract all of them. Each drug has properties like name and reaction. Since name is only one, it is a string, but there could be multiple reactions, hence it is a list. Similarly, users can define any schema for any type of entity.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -162,7 +163,8 @@ results.select("completions").show(truncate=False)
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -209,4 +211,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-04-jsl_meds_ner_q8_v2_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to extract and link entities in a document. Users needs to define an input schema as explained in the example section. Drug is defined as a list which tells the model that there could be multiple drugs in the document and it has to extract all of them. Each drug has properties like name and reaction. Since name is only one, it is a string, but there could be multiple reactions, hence it is a list. Similarly, users can define any schema for any type of entity.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -162,7 +163,8 @@ results.select("completions").show(truncate=False)
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -209,4 +211,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-04-jsl_meds_ner_zs_q16_v1_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to extract and link entities in a document. Users needs to define an input schema as explained in the example section. Drug is defined as a list which tells the model that there could be multiple drugs in the document and it has to extract all of them. Each drug has properties like name and reaction. Since “name” is only one, it is a string, but there could be multiple reactions, hence it is a list. Similarly, users can define any schema for any type of entity.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -162,7 +163,8 @@ results.select("completions").show(truncate=False)
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -209,4 +211,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-04-jsl_meds_ner_zs_q4_v1_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to extract and link entities in a document. Users needs to define an input schema as explained in the example section. Drug is defined as a list which tells the model that there could be multiple drugs in the document and it has to extract all of them. Each drug has properties like name and reaction. Since “name” is only one, it is a string, but there could be multiple reactions, hence it is a list. Similarly, users can define any schema for any type of entity.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -162,7 +163,8 @@ results.select("completions").show(truncate=False)
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -209,4 +211,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-04-jsl_meds_ner_zs_q8_v1_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to extract and link entities in a document. Users needs to define an input schema as explained in the example section. Drug is defined as a list which tells the model that there could be multiple drugs in the document and it has to extract all of them. Each drug has properties like name and reaction. Since “name” is only one, it is a string, but there could be multiple reactions, hence it is a list. Similarly, users can define any schema for any type of entity.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -163,7 +164,8 @@ results.select("completions").show(truncate=False)
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -210,4 +212,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-05-jsl_meds_q16_v1_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to perform Summarization and Q&A based on a given context.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -142,7 +143,8 @@ The age group most susceptible to breast cancer, as mentioned in the text, is wo
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -189,4 +191,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-05-jsl_meds_q16_v2_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to perform Q&A, Summarization, RAG, and Chat.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -134,7 +135,8 @@ The best treatment for this patient is E: Nitrofurantoin. This medication is con
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -181,4 +183,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-05-jsl_meds_q16_v3_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to perform Q&A, Summarization, RAG, and Chat.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -134,7 +135,8 @@ The best treatment for this patient is E: Nitrofurantoin. This medication is con
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall

docs/_posts/akrztrk/2024-10-05-jsl_meds_q4_v1_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to perform Summarization and Q&A based on a given context.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -141,7 +142,8 @@ The age group most susceptible to breast cancer, as mentioned in the text, is wo
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -188,4 +190,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-05-jsl_meds_q4_v2_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to perform Q&A, Summarization, RAG, and Chat.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -124,7 +125,8 @@ Hello! I am JSL Medical LLM, an artificial intelligence language model specializ
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -171,4 +173,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```

docs/_posts/akrztrk/2024-10-05-jsl_meds_q4_v3_en.md

@@ -21,6 +21,7 @@ use_language_switcher: "Python-Scala-Java"
 
 This LLM model is trained to perform Q&A, Summarization, RAG, and Chat.
 
+
 {:.btn-box}
 <button class="button button-orange" disabled>Live Demo</button>
 <button class="button button-orange" disabled>Open in Colab</button>
@@ -142,7 +143,8 @@ Based on the provided text, the age group most susceptible to breast cancer is w
 
 ## Benchmarking
 
-We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate
+We have generated a total of 400 questions, 100 from each category. These questions were labeled and reviewed by 3 physician annotators. `%` indicates the preference rate.
+Please see the more benchmark information [here](https://nlp.johnsnowlabs.com/docs/en/benchmark-llm).
 
 ```bash
 ## Overall
@@ -189,4 +191,4 @@ We have generated a total of 400 questions, 100 from each category. These questi
 | Neutral    | 0.19         | 0.20                 | 0.02          |
 | None       | 0.17         | 0.17                 | 0.19          |
 | Total      | 1.00         | 1.00                 | 1.00          |
-```
+```