[AI] Improve refdocs

The improvements include:

- Link directly to the list of supported models in the documentation.
- Fix rendering issues with numbers being translated as numbered lists
- Link to firebase documentation instead of vertex documentation when
corresponding.

Author: rlazo

firebase-ai/src/main/kotlin/com/google/firebase/ai/FirebaseAI.kt

@@ -51,7 +51,8 @@ internal constructor(
   /**
    * Instantiates a new [GenerativeModel] given the provided parameters.
    *
-   * @param modelName The name of the model to use, for example `"gemini-2.0-flash-exp"`.
+   * @param modelName The name of the model to use. See the documentation for a list of
+   *  [supported models](https://firebase.google.com/docs/ai-logic/models).
    * @param generationConfig The configuration parameters to use for content generation.
    * @param safetySettings The safety bounds the model will abide to during content generation.
    * @param tools A list of [Tool]s the model may use to generate content.
@@ -106,7 +107,8 @@ internal constructor(
   /**
    * Instantiates a new [LiveGenerationConfig] given the provided parameters.
    *
-   * @param modelName The name of the model to use, for example `"gemini-2.0-flash-exp"`.
+   * @param modelName The name of the model to use. See the documentation for a list of
+   *  [supported models](https://firebase.google.com/docs/ai-logic/models).
    * @param generationConfig The configuration parameters to use for content generation.
    * @param tools A list of [Tool]s the model may use to generate content.
    * @param systemInstruction [Content] instructions that direct the model to behave a certain way.
@@ -157,7 +159,8 @@ internal constructor(
   /**
    * Instantiates a new [ImagenModel] given the provided parameters.
    *
-   * @param modelName The name of the model to use, for example `"imagen-3.0-generate-001"`.
+   * @param modelName The name of the model to use. See the documentation for a list of
+   *  [supported models](https://firebase.google.com/docs/ai-logic/models).
    * @param generationConfig The configuration parameters to use for image generation.
    * @param safetySettings The safety bounds the model will abide by during image generation.
    * @param requestOptions Configuration options for sending requests to the backend.

firebase-ai/src/main/kotlin/com/google/firebase/ai/ImagenModel.kt

@@ -41,6 +41,9 @@ import com.google.firebase.auth.internal.InternalAuthProvider
 /**
  * Represents a generative model (like Imagen), capable of generating images based on various input
  * types.
+ *
+ * See the documentation for a list of
+ * [supported models](https://firebase.google.com/docs/ai-logic/models).
  */
 @PublicPreviewAPI
 public class ImagenModel

firebase-ai/src/main/kotlin/com/google/firebase/ai/type/Candidate.kt

@@ -76,8 +76,8 @@ internal constructor(
  *
  * @property category The category of harm being assessed (e.g., Hate speech).
  * @property probability The likelihood of the content causing harm.
- * @property probabilityScore A numerical score representing the probability of harm, between 0 and
- * 1.
+ * @property probabilityScore A numerical score representing the probability of harm, between `0`
+ * and `1`.
  * @property blocked Indicates whether the content was blocked due to safety concerns.
  * @property severity The severity of the potential harm.
  * @property severityScore A numerical score representing the severity of harm.

firebase-ai/src/main/kotlin/com/google/firebase/ai/type/CountTokensResponse.kt

@@ -22,14 +22,13 @@ import kotlinx.serialization.Serializable
  * The model's response to a count tokens request.
  *
  * **Important:** The counters in this class do not include billable image, video or other non-text
- * input. See [Vertex AI pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing) for
- * details.
+ * input. See [Pricing](https://firebase.google.com/docs/ai-logic/pricing) for details.
  *
  * @property totalTokens The total number of tokens in the input given to the model as a prompt.
  * @property totalBillableCharacters The total number of billable characters in the text input given
  * to the model as a prompt. **Important:** this property does not include billable image, video or
- * other non-text input. See
- * [Vertex AI pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing) for details.
+ * other non-text input. See [Pricing](https://firebase.google.com/docs/ai-logic/pricing) for
+ * details.
  * @property promptTokensDetails The breakdown, by modality, of how many tokens are consumed by the
  * prompt.
  */

firebase-ai/src/main/kotlin/com/google/firebase/ai/type/Part.kt

@@ -132,7 +132,7 @@ internal constructor(
  *
  * @param inlineData the binary data as a [ByteArray]
  * @param mimeType an IANA standard MIME type. For supported values, see the
- * [Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/send-multimodal-prompts#media_requirements)
+ * [Firebase documentation](https://firebase.google.com/docs/vertex-ai/input-file-requirements).
  */
 public class InlineDataPart
 internal constructor(