some fixes

Author: johnnygreco

docs/notebook_source/1-the-basics.py

@@ -72,20 +72,18 @@
 MODEL_ID = "nvidia/nemotron-3-nano-30b-a3b"
 
 # We choose this alias to be descriptive for our use case.
-MODEL_ALIAS = "nemotron-nano-v2"
-
-# This sets reasoning to False for the nemotron-nano-v2 model.
-SYSTEM_PROMPT = "/no_think"
+MODEL_ALIAS = "nemotron-nano-v3"
 
 model_configs = [
     ModelConfig(
         alias=MODEL_ALIAS,
         model=MODEL_ID,
         provider=MODEL_PROVIDER,
         inference_parameters=ChatCompletionInferenceParams(
-            temperature=0.5,
+            temperature=1.0,
             top_p=1.0,
-            max_tokens=1024,
+            max_tokens=2048,
+            extra_body={"chat_template_kwargs": {"enable_thinking": False}},
         ),
     )
 ]
@@ -252,7 +250,6 @@
             "on products related to '{{ product_subcategory }}'. The target age range of the ideal customer is "
             "{{ target_age_range }} years old. Respond with only the product name, no other text."
         ),
-        system_prompt=SYSTEM_PROMPT,
         model_alias=MODEL_ALIAS,
     )
 )
@@ -264,9 +261,9 @@
             "You are a customer named {{ customer.first_name }} from {{ customer.city }}, {{ customer.state }}. "
             "You are {{ customer.age }} years old and recently purchased a product called {{ product_name }}. "
             "Write a review of this product, which you gave a rating of {{ number_of_stars }} stars. "
-            "The style of the review should be '{{ review_style }}'."
+            "The style of the review should be '{{ review_style }}'. "
+            "Respond with only the review, no other text."
         ),
-        system_prompt=SYSTEM_PROMPT,
         model_alias=MODEL_ALIAS,
     )
 )

docs/notebook_source/2-structured-outputs-and-jinja-expressions.py

@@ -74,20 +74,18 @@
 MODEL_ID = "nvidia/nemotron-3-nano-30b-a3b"
 
 # We choose this alias to be descriptive for our use case.
-MODEL_ALIAS = "nemotron-nano-v2"
-
-# This sets reasoning to False for the nemotron-nano-v2 model.
-SYSTEM_PROMPT = "/no_think"
+MODEL_ALIAS = "nemotron-nano-v3"
 
 model_configs = [
     ModelConfig(
         alias=MODEL_ALIAS,
         model=MODEL_ID,
         provider=MODEL_PROVIDER,
         inference_parameters=ChatCompletionInferenceParams(
-            temperature=0.5,
+            temperature=1.0,
             top_p=1.0,
-            max_tokens=1024,
+            max_tokens=2048,
+            extra_body={"chat_template_kwargs": {"enable_thinking": False}},
         ),
     )
 ]
@@ -286,7 +284,6 @@ class ProductReview(BaseModel):
             "related to '{{ product_subcategory }}'. The target age range of the ideal customer is "
             "{{ target_age_range }} years old. The product should be priced between $10 and $1000."
         ),
-        system_prompt=SYSTEM_PROMPT,
         output_format=Product,
         model_alias=MODEL_ALIAS,
     )
@@ -304,12 +301,12 @@ class ProductReview(BaseModel):
             "Imagine your name is {{ customer_name }} and you are from {{ customer.city }}, {{ customer.state }}. "
             "Write the review in a style that is '{{ review_style }}'."
             "{% if target_age_range == '18-25' %}"
-            "Make sure the review is more informal and conversational."
+            "Make sure the review is more informal and conversational.\n"
             "{% else %}"
-            "Make sure the review is more formal and structured."
+            "Make sure the review is more formal and structured.\n"
             "{% endif %}"
+            "The review field should contain only the review, no other text."
         ),
-        system_prompt=SYSTEM_PROMPT,
         output_format=ProductReview,
         model_alias=MODEL_ALIAS,
     )

docs/notebook_source/3-seeding-with-a-dataset.py

@@ -68,20 +68,18 @@
 MODEL_ID = "nvidia/nemotron-3-nano-30b-a3b"
 
 # We choose this alias to be descriptive for our use case.
-MODEL_ALIAS = "nemotron-nano-v2"
-
-# This sets reasoning to False for the nemotron-nano-v2 model.
-SYSTEM_PROMPT = "/no_think"
+MODEL_ALIAS = "nemotron-nano-v3"
 
 model_configs = [
     ModelConfig(
         alias=MODEL_ALIAS,
         model=MODEL_ID,
         provider=MODEL_PROVIDER,
         inference_parameters=ChatCompletionInferenceParams(
-            temperature=0.5,
+            temperature=1.0,
             top_p=1.0,
-            max_tokens=1024,
+            max_tokens=2048,
+            extra_body={"chat_template_kwargs": {"enable_thinking": False}},
         ),
     )
 ]
@@ -220,9 +218,9 @@
 as Dr. {{ doctor_sampler.first_name }} {{ doctor_sampler.last_name }}.
 
 Format the notes as a busy doctor might.
+Respond with only the notes, no other text.
 """,
     model_alias=MODEL_ALIAS,
-    system_prompt=SYSTEM_PROMPT,
 )
 
 config_builder.validate()