spark-nlp 6.1.1__tar.gz → 6.1.2rc1__tar.gz

{spark_nlp-6.1.1 → spark_nlp-6.1.2rc1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.1
+Version: 6.1.2rc1
 Summary: John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
 Home-page: https://github.com/JohnSnowLabs/spark-nlp
 Author: John Snow Labs

{spark_nlp-6.1.1 → spark_nlp-6.1.2rc1}/setup.py

@@ -41,7 +41,7 @@ setup(
     # project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
 
-    version='6.1.1',  # Required
+    version='6.1.2-rc1',  # Required
 
     # This is a one-line description or tagline of what your project does. This
     # corresponds to the 'Summary' metadata field:

{spark_nlp-6.1.1 → spark_nlp-6.1.2rc1}/spark_nlp.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: spark-nlp
-Version: 6.1.1
+Version: 6.1.2rc1
 Summary: John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML. It provides simple, performant & accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.
 Home-page: https://github.com/JohnSnowLabs/spark-nlp
 Author: John Snow Labs

{spark_nlp-6.1.1 → spark_nlp-6.1.2rc1}/sparknlp/annotator/seq2seq/auto_gguf_model.py

@@ -260,13 +260,13 @@ class AutoGGUFModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties):
         )
 
     @staticmethod
-    def loadSavedModel(folder, spark_session):
+    def loadSavedModel(path, spark_session):
         """Loads a locally saved model.
 
         Parameters
         ----------
-        folder : str
-            Folder of the saved model
+        path : str
+            Path to the gguf model
         spark_session : pyspark.sql.SparkSession
             The current SparkSession
 
@@ -276,7 +276,7 @@ class AutoGGUFModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppProperties):
             The restored model
         """
         from sparknlp.internal import _AutoGGUFLoader
-        jModel = _AutoGGUFLoader(folder, spark_session._jsparkSession)._java_obj
+        jModel = _AutoGGUFLoader(path, spark_session._jsparkSession)._java_obj
         return AutoGGUFModel(java_model=jModel)
 
     @staticmethod

{spark_nlp-6.1.1 → spark_nlp-6.1.2rc1}/sparknlp/annotator/seq2seq/auto_gguf_vision_model.py

@@ -116,8 +116,6 @@ class AutoGGUFVisionModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppPropert
         Set optimization strategies that help on some NUMA systems (if available)
     ropeScalingType
         Set the RoPE frequency scaling method, defaults to linear unless specified by the model
-    poolingType
-        Set the pooling type for embeddings, use model default if unspecified
     modelDraft
         Set the draft model for speculative decoding
     modelAlias
@@ -126,8 +124,6 @@ class AutoGGUFVisionModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppPropert
         Set path to static lookup cache to use for lookup decoding (not updated by generation)
     lookupCacheDynamicFilePath
         Set path to dynamic lookup cache to use for lookup decoding (updated by generation)
-    embedding
-        Whether to load model with embedding support
     flashAttention
         Whether to enable Flash Attention
     inputPrefixBos
@@ -284,8 +280,10 @@ class AutoGGUFVisionModel(AnnotatorModel, HasBatchedAnnotate, HasLlamaCppPropert
             useChatTemplate=True,
             nCtx=4096,
             nBatch=512,
-            embedding=False,
-            nPredict=100
+            nPredict=100,
+            nGpuLayers=99,
+            systemPrompt="You are a helpful assistant.",
+            batchSize=2,
         )
 
     @staticmethod