fine tuning api接口类型兼容修改

Author: Lambdua

api/src/main/java/com/theokanning/openai/fine_tuning/Hyperparameters.java

@@ -17,23 +17,26 @@
 @Data
 public class Hyperparameters {
     /**
+     * String or Integer type
      * The number of epochs to train the model for.
      * An epoch refers to one full cycle through the training dataset.
      * "Auto" decides the optimal number of epochs based on the size of the dataset.
      * If setting the number manually, we support any number between 1 and 50 epochs.
      */
     @JsonProperty("n_epochs")
-    Integer nEpochs;
+    Object nEpochs;
 
     /**
+     * String or Integer type
      * Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance.
      */
     @JsonProperty("batch_size")
-    Integer batchSize;
+    Object batchSize;
 
     /**
+     * double or String type
      * Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting.
      */
     @JsonProperty("learning_rate_multiplier")
-    Double learningRateMultiplier;
+    Object learningRateMultiplier;
 }

service/src/test/java/com/theokanning/openai/service/FineTuningTest.java

@@ -44,7 +44,7 @@ void createFineTuningJob() {
                 .build();
         FineTuningJobRequest request = FineTuningJobRequest.builder()
                 .trainingFile(fileId)
-                .model("gpt-4o-mini")
+                .model("gpt-3.5-turbo")
                 .hyperparameters(hyperparameters)
                 .build();
 
@@ -74,7 +74,7 @@ void listFineTuningEvents() {
     void retrieveFineTuningJob() {
         FineTuningJob fineTune = service.retrieveFineTuningJob(fineTuningJobId);
 
-        assertTrue(fineTune.getModel().startsWith("gpt-4o-mini"));
+        assertTrue(fineTune.getModel().startsWith("gpt-3.5-turbo"));
     }
 
     @Test