refactor variable names

geniusrise_huggingface/__init__.py

@@ -20,6 +20,5 @@
 from geniusrise_huggingface.language_model import HuggingFaceLanguageModelingFineTuner
 from geniusrise_huggingface.ner import HuggingFaceNamedEntityRecognitionFineTuner
 from geniusrise_huggingface.question_answering import HuggingFaceQuestionAnsweringFineTuner
-from geniusrise_huggingface.sentiment_analysis import HuggingFaceSentimentAnalysisFineTuner
 from geniusrise_huggingface.summarization import HuggingFaceSummarizationFineTuner
 from geniusrise_huggingface.translation import HuggingFaceTranslationFineTuner

geniusrise_huggingface/base/api.py

@@ -32,8 +32,8 @@ class HuggingFaceAPI(HuggingFaceBulk):
         model_revision (Optional[str]): The revision of the pre-trained language model.
         tokenizer_name (str): The name of the tokenizer used to preprocess input text.
         tokenizer_revision (Optional[str]): The revision of the tokenizer used to preprocess input text.
-        model_class_name (str): The name of the class of the pre-trained language model.
-        tokenizer_class_name (str): The name of the class of the tokenizer used to preprocess input text.
+        model_class (str): The name of the class of the pre-trained language model.
+        tokenizer_class (str): The name of the class of the tokenizer used to preprocess input text.
         use_cuda (bool): Whether to use a GPU for inference.
         quantization (int): The level of quantization to use for the pre-trained language model.
         precision (str): The precision to use for the pre-trained language model.
@@ -46,7 +46,7 @@ class HuggingFaceAPI(HuggingFaceBulk):
         text(**kwargs: Any) -> Dict[str, Any]:
             Generates text based on the given prompt and decoding strategy.
 
-        listen(model_name: str, model_class_name: str = "AutoModelForCausalLM", tokenizer_class_name: str = "AutoTokenizer", use_cuda: bool = False, precision: str = "float16", quantization: int = 0, device_map: str | Dict | None = "auto", max_memory={0: "24GB"}, torchscript: bool = True, endpoint: str = "*", port: int = 3000, cors_domain: str = "http://localhost:3000", username: Optional[str] = None, password: Optional[str] = None, **model_args: Any) -> None:
+        listen(model_name: str, model_class: str = "AutoModelForCausalLM", tokenizer_class: str = "AutoTokenizer", use_cuda: bool = False, precision: str = "float16", quantization: int = 0, device_map: str | Dict | None = "auto", max_memory={0: "24GB"}, torchscript: bool = True, endpoint: str = "*", port: int = 3000, cors_domain: str = "http://localhost:3000", username: Optional[str] = None, password: Optional[str] = None, **model_args: Any) -> None:
             Starts a CherryPy server to listen for requests to generate text.
     """
 
@@ -118,8 +118,8 @@ def text(self, **kwargs: Any) -> Dict[str, Any]:
     def listen(
         self,
         model_name: str,
-        model_class_name: str = "AutoModelForCausalLM",
-        tokenizer_class_name: str = "AutoTokenizer",
+        model_class: str = "AutoModelForCausalLM",
+        tokenizer_class: str = "AutoTokenizer",
         use_cuda: bool = False,
         precision: str = "float16",
         quantization: int = 0,
@@ -138,8 +138,8 @@ def listen(
 
         Args:
             model_name (str): The name of the pre-trained language model.
-            model_class_name (str, optional): The name of the class of the pre-trained language model. Defaults to "AutoModelForCausalLM".
-            tokenizer_class_name (str, optional): The name of the class of the tokenizer used to preprocess input text. Defaults to "AutoTokenizer".
+            model_class (str, optional): The name of the class of the pre-trained language model. Defaults to "AutoModelForCausalLM".
+            tokenizer_class (str, optional): The name of the class of the tokenizer used to preprocess input text. Defaults to "AutoTokenizer".
             use_cuda (bool, optional): Whether to use a GPU for inference. Defaults to False.
             precision (str, optional): The precision to use for the pre-trained language model. Defaults to "float16".
             quantization (int, optional): The level of quantization to use for the pre-trained language model. Defaults to 0.
@@ -154,8 +154,8 @@ def listen(
             **model_args (Any): Additional arguments to pass to the pre-trained language model.
         """
         self.model_name = model_name
-        self.model_class_name = model_class_name
-        self.tokenizer_class_name = tokenizer_class_name
+        self.model_class = model_class
+        self.tokenizer_class = tokenizer_class
         self.use_cuda = use_cuda
         self.quantization = quantization
         self.precision = precision
@@ -182,8 +182,8 @@ def listen(
             tokenizer_name=self.tokenizer_name,
             model_revision=self.model_revision,
             tokenizer_revision=self.tokenizer_revision,
-            model_class_name=self.model_class_name,
-            tokenizer_class_name=self.tokenizer_class_name,
+            model_class=self.model_class,
+            tokenizer_class=self.tokenizer_class,
             use_cuda=self.use_cuda,
             precision=self.precision,
             quantization=self.quantization,

geniusrise_huggingface/base/bulk.py

@@ -205,8 +205,8 @@ def load_models(
         tokenizer_name: str,
         model_revision: Optional[str] = None,
         tokenizer_revision: Optional[str] = None,
-        model_class_name: str = "AutoModelForCausalLM",
-        tokenizer_class_name: str = "AutoTokenizer",
+        model_class: str = "AutoModelForCausalLM",
+        tokenizer_class: str = "AutoTokenizer",
         use_cuda: bool = False,
         precision: str = "float16",
         quantization: int = 0,
@@ -220,8 +220,8 @@ def load_models(
 
         Parameters:
         - model_name (str): The name of the model to load.
-        - model_class_name (str): The class name of the model to load. Default is "AutoModelForCausalLM".
-        - tokenizer_class_name (str): The class name of the tokenizer to load. Default is "AutoTokenizer".
+        - model_class (str): The class name of the model to load. Default is "AutoModelForCausalLM".
+        - tokenizer_class (str): The class name of the tokenizer to load. Default is "AutoTokenizer".
         - use_cuda (bool): Whether to use CUDA for GPU acceleration. Default is False.
         - precision (str): The bit precision for model and tokenizer. Options are 'float32', 'float16', 'bfloat16'. Default is 'float16'.
         - device_map (Union[str, Dict]): Device map for model placement. Default is "auto".
@@ -251,8 +251,8 @@ def load_models(
         if use_cuda and not device_map:
             device_map = "auto"
 
-        ModelClass = getattr(transformers, model_class_name)
-        TokenizerClass = getattr(transformers, tokenizer_class_name)
+        ModelClass = getattr(transformers, model_class)
+        TokenizerClass = getattr(transformers, tokenizer_class)
 
         # Load the model and tokenizer
         tokenizer = TokenizerClass.from_pretrained(tokenizer_name, revision=tokenizer_revision, torch_dtype=torch_dtype)

geniusrise_huggingface/base/tests/test_api.py

@@ -25,7 +25,7 @@
 
 @pytest.fixture(
     params=[
-        # model_name, model_class_name, tokenizer_class_name, use_cuda, precision, quantization, device_map, max_memory, torchscript
+        # model_name, model_class, tokenizer_class, use_cuda, precision, quantization, device_map, max_memory, torchscript
         # fmt: off
         ("gpt2", "AutoModelForCausalLM", "AutoTokenizer", True, "float16", 0, None, None, False),
         ("gpt2", "AutoModelForCausalLM", "AutoTokenizer", False, "float32", 0, None, None, False),
@@ -72,8 +72,8 @@ def hfa():
 def test_load_models(hfa, model_config):
     (
         model_name,
-        model_class_name,
-        tokenizer_class_name,
+        model_class,
+        tokenizer_class,
         use_cuda,
         precision,
         quantization,
@@ -97,8 +97,8 @@ def test_load_models(hfa, model_config):
         model_revision=model_revision,
         tokenizer_name=model_name,
         tokenizer_revision=tokenizer_revision,
-        model_class_name=model_class_name,
-        tokenizer_class_name=tokenizer_class_name,
+        model_class=model_class,
+        tokenizer_class=tokenizer_class,
         use_cuda=use_cuda,
         precision=precision,
         quantization=quantization,
@@ -149,8 +149,8 @@ def test_load_models(hfa, model_config):
 def test_generate_strategies(hfa, model_config, strategy):
     (
         model_name,
-        model_class_name,
-        tokenizer_class_name,
+        model_class,
+        tokenizer_class,
         use_cuda,
         precision,
         quantization,
@@ -174,8 +174,8 @@ def test_generate_strategies(hfa, model_config, strategy):
         model_revision=model_revision,
         tokenizer_name=model_name,
         tokenizer_revision=tokenizer_revision,
-        model_class_name=model_class_name,
-        tokenizer_class_name=tokenizer_class_name,
+        model_class=model_class,
+        tokenizer_class=tokenizer_class,
         use_cuda=use_cuda,
         precision=precision,
         quantization=quantization,

geniusrise_huggingface/base/tests/test_bulk.py

@@ -25,7 +25,7 @@
 
 @pytest.fixture(
     params=[
-        # model_name, model_class_name, tokenizer_class_name, use_cuda, precision, quantization, device_map, max_memory, torchscript
+        # model_name, model_class, tokenizer_class, use_cuda, precision, quantization, device_map, max_memory, torchscript
         # fmt: off
         ("gpt2", "AutoModelForCausalLM", "AutoTokenizer", True, "float16", 0, None, None, False),
         ("gpt2", "AutoModelForCausalLM", "AutoTokenizer", False, "float32", 0, None, None, False),
@@ -72,8 +72,8 @@ def hfa():
 def test_load_models(hfa, model_config):
     (
         model_name,
-        model_class_name,
-        tokenizer_class_name,
+        model_class,
+        tokenizer_class,
         use_cuda,
         precision,
         quantization,
@@ -97,8 +97,8 @@ def test_load_models(hfa, model_config):
         model_revision=model_revision,
         tokenizer_name=model_name,
         tokenizer_revision=tokenizer_revision,
-        model_class_name=model_class_name,
-        tokenizer_class_name=tokenizer_class_name,
+        model_class=model_class,
+        tokenizer_class=tokenizer_class,
         use_cuda=use_cuda,
         precision=precision,
         quantization=quantization,
@@ -149,8 +149,8 @@ def test_load_models(hfa, model_config):
 def test_generate_strategies(hfa, model_config, strategy):
     (
         model_name,
-        model_class_name,
-        tokenizer_class_name,
+        model_class,
+        tokenizer_class,
         use_cuda,
         precision,
         quantization,
@@ -174,8 +174,8 @@ def test_generate_strategies(hfa, model_config, strategy):
         model_revision=model_revision,
         tokenizer_name=model_name,
         tokenizer_revision=tokenizer_revision,
-        model_class_name=model_class_name,
-        tokenizer_class_name=tokenizer_class_name,
+        model_class=model_class,
+        tokenizer_class=tokenizer_class,
         use_cuda=use_cuda,
         precision=precision,
         quantization=quantization,

geniusrise_huggingface/embeddings/api.py

@@ -45,8 +45,8 @@ class EmbeddingsAPI(HuggingFaceAPI):
     genius EmbeddingsAPI rise \
         listen \
             --model_name=bert-base-uncased \
-            --model_class_name=AutoModelForCausalLM \
-            --tokenizer_class_name=AutoTokenizer \
+            --model_class=AutoModelForCausalLM \
+            --tokenizer_class=AutoTokenizer \
             --sentence_transformer_model=paraphrase-MiniLM-L6-v2 \
             --use_cuda=True \
             --precision=float16 \
@@ -68,8 +68,8 @@ class EmbeddingsAPI(HuggingFaceAPI):
             method: "listen"
             args:
                 model_name: "bert-base-uncased"
-                model_class_name: "AutoModelForCausalLM"
-                tokenizer_class_name: "AutoTokenizer"
+                model_class: "AutoModelForCausalLM"
+                tokenizer_class: "AutoTokenizer"
                 sentence_transformer_model: "paraphrase-MiniLM-L6-v2"
                 use_cuda: True
                 precision: "float16"
@@ -234,8 +234,8 @@ def sentence_permutations(self, **kwargs: Any) -> Dict[str, Any]:
     def listen(  # type: ignore
         self,
         model_name: str,
-        model_class_name: str = "AutoModelForCausalLM",
-        tokenizer_class_name: str = "AutoTokenizer",
+        model_class: str = "AutoModelForCausalLM",
+        tokenizer_class: str = "AutoTokenizer",
         use_cuda: bool = False,
         precision: str = "float16",
         quantization: int = 0,
@@ -254,8 +254,8 @@ def listen(  # type: ignore
 
         Parameters:
         - model_name (str): The name of the Hugging Face model to use.
-        - model_class_name (str, optional): The class name of the model. Defaults to "AutoModelForCausalLM".
-        - tokenizer_class_name (str, optional): The class name of the tokenizer. Defaults to "AutoTokenizer".
+        - model_class (str, optional): The class name of the model. Defaults to "AutoModelForCausalLM".
+        - tokenizer_class (str, optional): The class name of the tokenizer. Defaults to "AutoTokenizer".
         - sentence_transformer_model (str, optional): The name of the Sentence Transformer model to use. Defaults to "paraphrase-MiniLM-L6-v2".
         - use_cuda (bool, optional): Whether to use CUDA for computation. Defaults to False.
         - precision (str, optional): The precision to use for computations. Defaults to "float16".
@@ -273,8 +273,8 @@ def listen(  # type: ignore
         None
         """
         self.model_name = model_name
-        self.model_class_name = model_class_name
-        self.tokenizer_class_name = tokenizer_class_name
+        self.model_class = model_class
+        self.tokenizer_class = tokenizer_class
         self.use_cuda = use_cuda
         self.quantization = quantization
         self.precision = precision
@@ -302,8 +302,8 @@ def listen(  # type: ignore
             tokenizer_name=self.tokenizer_name,
             model_revision=self.model_revision,
             tokenizer_revision=self.tokenizer_revision,
-            model_class_name=self.model_class_name,
-            tokenizer_class_name=self.tokenizer_class_name,
+            model_class=self.model_class,
+            tokenizer_class=self.tokenizer_class,
             use_cuda=self.use_cuda,
             precision=self.precision,
             quantization=self.quantization,

geniusrise_huggingface/embeddings/bulk.py

@@ -102,8 +102,8 @@ def load_models(
         tokenizer_name: str,
         model_revision: Optional[str] = None,
         tokenizer_revision: Optional[str] = None,
-        model_class_name: str = "AutoModelForCausalLM",
-        tokenizer_class_name: str = "AutoTokenizer",
+        model_class: str = "AutoModelForCausalLM",
+        tokenizer_class: str = "AutoTokenizer",
         use_cuda: bool = False,
         precision: str = "float16",
         quantization: int = 0,
@@ -117,8 +117,8 @@ def load_models(
 
         Parameters:
         - model_name (str): The name of the model to load.
-        - model_class_name (str): The class name of the model to load. Default is "AutoModelForCausalLM".
-        - tokenizer_class_name (str): The class name of the tokenizer to load. Default is "AutoTokenizer".
+        - model_class (str): The class name of the model to load. Default is "AutoModelForCausalLM".
+        - tokenizer_class (str): The class name of the tokenizer to load. Default is "AutoTokenizer".
         - use_cuda (bool): Whether to use CUDA for GPU acceleration. Default is False.
         - precision (str): The bit precision for model and tokenizer. Options are 'float32', 'float16', 'bfloat16'. Default is 'float16'.
         - device_map (Union[str, Dict]): Device map for model placement. Default is "auto".
@@ -148,8 +148,8 @@ def load_models(
         if use_cuda and not device_map:
             device_map = "auto"
 
-        ModelClass = getattr(transformers, model_class_name)
-        TokenizerClass = getattr(transformers, tokenizer_class_name)
+        ModelClass = getattr(transformers, model_class)
+        TokenizerClass = getattr(transformers, tokenizer_class)
 
         # Load the model and tokenizer
         tokenizer = TokenizerClass.from_pretrained(tokenizer_name, revision=tokenizer_revision, torch_dtype=torch_dtype)
@@ -199,8 +199,8 @@ def generate(
         self,
         kind: str,
         model_name: str,
-        model_class_name: str = "AutoModelForCausalLM",
-        tokenizer_class_name: str = "AutoTokenizer",
+        model_class: str = "AutoModelForCausalLM",
+        tokenizer_class: str = "AutoTokenizer",
         sentence_transformer_model: str = "paraphrase-MiniLM-L6-v2",
         use_cuda: bool = False,
         precision: str = "float16",
@@ -220,8 +220,8 @@ def generate(
         This method reads text data from the specified input path, generates embeddings, and saves them to the specified output path.
         """
         self.model_name = model_name
-        self.model_class_name = model_class_name
-        self.tokenizer_class_name = tokenizer_class_name
+        self.model_class = model_class
+        self.tokenizer_class = tokenizer_class
         self.use_cuda = use_cuda
         self.quantization = quantization
         self.precision = precision
@@ -255,8 +255,8 @@ def generate(
                 tokenizer_name=self.tokenizer_name,
                 model_revision=self.model_revision,
                 tokenizer_revision=self.tokenizer_revision,
-                model_class_name=self.model_class_name,
-                tokenizer_class_name=self.tokenizer_class_name,
+                model_class=self.model_class,
+                tokenizer_class=self.tokenizer_class,
                 use_cuda=self.use_cuda,
                 precision=self.precision,
                 quantization=self.quantization,