omnigenome 0.3.0a0__py3-none-any.whl → 0.3.1a0__py3-none-any.whl

omnigenome/utility/pipeline_hub/pipeline.py

@@ -31,12 +31,12 @@ from ...src.trainer.trainer import Trainer
 class Pipeline:
     """
     Complete machine learning pipeline combining model, tokenizer, datasets, and trainer.
-    
+
     The Pipeline class provides a unified interface for managing complete machine
     learning workflows. It handles model initialization, training, inference, and
     persistence. Pipelines can be loaded from pre-built configurations or created
     from scratch with custom components.
-    
+
     Attributes:
         model (OmniModel): The underlying model for the pipeline.
         tokenizer: Tokenizer for preprocessing input sequences.
@@ -45,7 +45,7 @@ class Pipeline:
         trainer (Trainer): Trainer instance for model training.
         device (str): Target device for model execution (CPU/GPU).
         name (str): Name identifier for the pipeline.
-    
+
     Example:
         >>> from omnigenome import Pipeline, OmniModelForSequenceClassification
         >>> # Create pipeline from model
@@ -57,14 +57,14 @@ class Pipeline:
         >>> pipeline.train(datasets)
         >>> # Save pipeline
         >>> pipeline.save("./saved_pipeline")
-    
+
     Note:
         - Pipelines automatically handle device placement and model optimization
         - Environment metadata is collected for reproducibility
         - Pipelines can be saved and loaded for easy deployment
         - Supports both local models and hub-based model loading
     """
-    
+
     model: OmniModel = None
     tokenizer = None
     dataset: dict = None
@@ -82,7 +82,7 @@ class Pipeline:
     ):
         """
         Initialize a Pipeline instance.
-        
+
         Args:
             name (str): Name identifier for the pipeline.
             model_name_or_path (Union[str, OmniModel]): Model to use in the pipeline.
@@ -97,20 +97,20 @@ class Pipeline:
                 - device (str): Target device for model execution
                 - trust_remote_code (bool): Whether to trust remote code in tokenizers
                 - Other model-specific configuration parameters
-        
+
         Raises:
             ValueError: If model initialization fails.
             ImportError: If required dependencies are not available.
             FileNotFoundError: If model path is invalid.
-        
+
         Example:
             >>> # Create from model path
-            >>> pipeline = Pipeline("rna_classification", 
+            >>> pipeline = Pipeline("rna_classification",
             ...                    model_name_or_path="yangheng/OmniGenome-186M")
             >>> # Create from model instance
             >>> model = OmniModelForSequenceClassification("model_path", tokenizer)
             >>> pipeline = Pipeline("custom_pipeline", model_name_or_path=model)
-        
+
         Note:
             - The pipeline automatically handles model loading and device placement
             - Environment metadata is collected for tracking system information
@@ -140,18 +140,18 @@ class Pipeline:
     def __call__(self, inputs, *args, **kwargs):
         """
         Call the pipeline for inference.
-        
+
         This method provides a convenient interface for running inference
         through the pipeline. It delegates to the model's inference method.
-        
+
         Args:
             inputs: Input data for inference (can be string, list, or tensor).
             *args: Additional positional arguments passed to model inference.
             **kwargs: Additional keyword arguments passed to model inference.
-        
+
         Returns:
             dict: Inference results including predictions and confidence scores.
-        
+
         Example:
             >>> pipeline = Pipeline("my_pipeline", model_name_or_path=model)
             >>> results = pipeline("ATCGATCG")
@@ -162,13 +162,13 @@ class Pipeline:
     def to(self, device):
         """
         Move the pipeline to a specific device.
-        
+
         Args:
             device (str): Target device ('cpu', 'cuda', 'cuda:0', etc.).
-        
+
         Returns:
             Pipeline: Self for method chaining.
-        
+
         Example:
             >>> pipeline = Pipeline("my_pipeline", model_name_or_path=model)
             >>> pipeline.to("cuda:0")  # Move to GPU
@@ -181,11 +181,11 @@ class Pipeline:
     def init_pipeline(self, *, model_name_or_path, tokenizer=None, **kwargs):
         """
         Initialize the pipeline components from a model path.
-        
+
         This method handles loading the model, tokenizer, and configuration
         from a model path or identifier. It tries to load from the ModelHub
         first, then falls back to HuggingFace transformers.
-        
+
         Args:
             model_name_or_path (str): Path or identifier of the model to load.
             tokenizer (optional): Tokenizer instance. If None, will be loaded
@@ -194,18 +194,18 @@ class Pipeline:
                 - trust_remote_code (bool): Whether to trust remote code
                 - device (str): Target device for the model
                 - Other model-specific parameters
-        
+
         Returns:
             Pipeline: Self for method chaining.
-        
+
         Raises:
             ValueError: If model loading fails.
             ImportError: If required dependencies are not available.
-        
+
         Example:
             >>> pipeline = Pipeline("my_pipeline")
             >>> pipeline.init_pipeline(model_name_or_path="yangheng/OmniGenome-186M")
-        
+
         Note:
             - First attempts to load from OmniGenome ModelHub
             - Falls back to HuggingFace transformers if ModelHub fails
@@ -241,11 +241,11 @@ class Pipeline:
     def train(self, datasets: dict = None, trainer=None, **kwargs):
         """
         Train the model in the pipeline.
-        
+
         This method initiates training of the model using the provided datasets
         and trainer configuration. If no trainer is provided, the pipeline's
         existing trainer will be used.
-        
+
         Args:
             datasets (dict, optional): Dictionary containing train/validation/test
                 datasets. If None, uses the pipeline's existing datasets.
@@ -253,11 +253,11 @@ class Pipeline:
             trainer (Trainer, optional): Trainer instance to use for training.
                 If None, uses the pipeline's existing trainer. Defaults to None.
             **kwargs: Additional keyword arguments passed to the trainer.
-        
+
         Raises:
             ValueError: If no trainer is available or datasets are invalid.
             RuntimeError: If training fails.
-        
+
         Example:
             >>> pipeline = Pipeline("my_pipeline", model_name_or_path=model)
             >>> # Train with existing datasets
@@ -269,7 +269,7 @@ class Pipeline:
             >>> from omnigenome import Trainer
             >>> custom_trainer = Trainer(model, train_dataset=train_data)
             >>> pipeline.train(trainer=custom_trainer)
-        
+
         Note:
             - Training uses the pipeline's current model and device
             - Progress and metrics are logged during training
@@ -284,24 +284,24 @@ class Pipeline:
     def predict(self, inputs, **kwargs):
         """
         Generate predictions for input data.
-        
+
         This method provides a high-level interface for generating predictions
         from the pipeline's model. It handles preprocessing and postprocessing
         automatically.
-        
+
         Args:
             inputs: Input data for prediction. Can be:
                 - str: Single sequence string
                 - list: List of sequence strings
                 - tensor: Preprocessed input tensors
             **kwargs: Additional keyword arguments passed to model prediction.
-        
+
         Returns:
             dict: Prediction results including:
                 - predictions: Predicted labels or values
                 - confidence: Confidence scores (if available)
                 - logits: Raw model outputs (if requested)
-        
+
         Example:
             >>> pipeline = Pipeline("my_pipeline", model_name_or_path=model)
             >>> # Single prediction
@@ -310,7 +310,7 @@ class Pipeline:
             >>> # Batch prediction
             >>> results = pipeline.predict(["ATCGATCG", "GCTAGCTA"])
             >>> print(results['predictions'])
-        
+
         Note:
             - Input preprocessing is handled automatically
             - Results are formatted consistently across different model types
@@ -321,11 +321,11 @@ class Pipeline:
     def inference(self, inputs, **kwargs):
         """
         Run full inference pipeline on input data.
-        
+
         This method provides the complete inference pipeline including
         preprocessing, model forward pass, and postprocessing. It's the
         recommended method for production inference.
-        
+
         Args:
             inputs: Input data for inference. Can be:
                 - str: Single sequence string
@@ -335,14 +335,14 @@ class Pipeline:
                 - return_attention: Whether to return attention weights
                 - return_hidden_states: Whether to return hidden states
                 - temperature: Temperature for sampling (if applicable)
-        
+
         Returns:
             dict: Complete inference results including:
                 - predictions: Final predictions
                 - confidence: Confidence scores
                 - attention: Attention weights (if requested)
                 - hidden_states: Hidden states (if requested)
-        
+
         Example:
             >>> pipeline = Pipeline("my_pipeline", model_name_or_path=model)
             >>> # Basic inference
@@ -351,7 +351,7 @@ class Pipeline:
             >>> # Inference with attention
             >>> results = pipeline.inference("ATCGATCG", return_attention=True)
             >>> print(results['attention'].shape)
-        
+
         Note:
             - This is the most comprehensive inference method
             - Handles all preprocessing and postprocessing automatically
@@ -363,10 +363,10 @@ class Pipeline:
     def load(pipeline_name_or_path, local_only=False, **kwargs):
         """
         Load a pipeline from disk or hub.
-        
+
         This static method loads a complete pipeline including model, tokenizer,
         datasets, and trainer from a saved pipeline directory or hub identifier.
-        
+
         Args:
             pipeline_name_or_path (str): Path to saved pipeline directory or
                 hub identifier for downloading.
@@ -376,16 +376,16 @@ class Pipeline:
                 - device: Target device for the model
                 - name: Custom name for the pipeline
                 - trust_remote_code: Whether to trust remote code
-        
+
         Returns:
             Pipeline: Loaded pipeline instance ready for use.
-        
+
         Raises:
             FileNotFoundError: If pipeline cannot be found locally and
                 local_only is True.
             ValueError: If pipeline files are corrupted or invalid.
             ImportError: If required dependencies are not available.
-        
+
         Example:
             >>> # Load from local path
             >>> pipeline = Pipeline.load("./saved_pipeline")
@@ -393,7 +393,7 @@ class Pipeline:
             >>> pipeline = Pipeline.load("yangheng/OmniGenome-RNA-Classification")
             >>> # Use loaded pipeline
             >>> results = pipeline("ATCGATCG")
-        
+
         Note:
             - Loads all pipeline components (model, tokenizer, datasets, trainer)
             - Automatically handles device placement
@@ -430,22 +430,22 @@ class Pipeline:
     def save(self, path, overwrite=False, **kwargs):
         """
         Save the pipeline to disk.
-        
+
         This method saves the complete pipeline including model, tokenizer,
         datasets, trainer, and metadata to a directory. The saved pipeline
         can be loaded later using Pipeline.load().
-        
+
         Args:
             path (str): Directory path where to save the pipeline.
             overwrite (bool, optional): If True, overwrite existing directory.
                 If False, raise error if directory exists. Defaults to False.
             **kwargs: Additional keyword arguments for model saving.
-        
+
         Raises:
             FileExistsError: If path exists and overwrite is False.
             OSError: If there are issues creating the directory or writing files.
             RuntimeError: If saving fails due to model or data issues.
-        
+
         Example:
             >>> pipeline = Pipeline("my_pipeline", model_name_or_path=model)
             >>> # Train the pipeline
@@ -454,7 +454,7 @@ class Pipeline:
             >>> pipeline.save("./trained_pipeline", overwrite=True)
             >>> # Load the saved pipeline later
             >>> loaded_pipeline = Pipeline.load("./trained_pipeline")
-        
+
         Note:
             - Saves all pipeline components (model, tokenizer, datasets, trainer)
             - Preserves training configurations and metadata

omnigenome/utility/pipeline_hub/pipeline_hub.py

@@ -21,37 +21,37 @@ from ...src.misc.utils import env_meta_info
 class PipelineHub:
     """
     Hub for managing and loading pre-built OmniGenome pipelines.
-    
+
     The PipelineHub provides a centralized interface for accessing pre-built
     pipelines that combine models, tokenizers, datasets, and training
     configurations. It handles automatic downloading and loading of pipelines
     from the OmniGenome hub.
-    
+
     Attributes:
         metadata (dict): Environment metadata including system information,
             package versions, and hardware details.
-    
+
     Example:
         >>> from omnigenome import PipelineHub
         >>> hub = PipelineHub()
         >>> pipeline = hub.load("yangheng/OmniGenome-RNA-Classification")
         >>> predictions = pipeline("ATCGATCG")
         >>> print(predictions['predictions'])
-    
+
     Note:
         - Pipelines can be loaded from local paths or downloaded from the hub
         - The hub automatically handles model, tokenizer, and dataset loading
         - Environment metadata is collected for reproducibility
     """
-    
+
     def __init__(self, *args, **kwargs):
         """
         Initialize the PipelineHub.
-        
+
         Args:
             *args: Variable length argument list (currently unused).
             **kwargs: Arbitrary keyword arguments (currently unused).
-        
+
         Note:
             The constructor initializes environment metadata for tracking
             system information and package versions.
@@ -63,11 +63,11 @@ class PipelineHub:
     def load(pipeline_name_or_path, local_only=False, **kwargs):
         """
         Load a pipeline from the hub or local path.
-        
+
         This method loads a complete pipeline including the model, tokenizer,
         datasets, and trainer configuration. If the pipeline doesn't exist
         locally and local_only is False, it will be downloaded from the hub.
-        
+
         Args:
             pipeline_name_or_path (str): Name or path of the pipeline to load.
                 Can be a local directory path or a hub identifier.
@@ -78,17 +78,17 @@ class PipelineHub:
                 - device: Target device for the model
                 - trust_remote_code: Whether to trust remote code in tokenizers
                 - name: Custom name for the pipeline
-        
+
         Returns:
             Pipeline: Loaded pipeline instance with model, tokenizer, datasets,
                 and trainer ready for use.
-        
+
         Raises:
             FileNotFoundError: If the pipeline cannot be found locally and
                 local_only is True.
             ValueError: If the pipeline configuration is invalid.
             ImportError: If required dependencies are not available.
-        
+
         Example:
             >>> hub = PipelineHub()
             >>> # Load from hub
@@ -97,7 +97,7 @@ class PipelineHub:
             >>> pipeline = hub.load("./my_pipeline", local_only=True)
             >>> # Use pipeline for inference
             >>> results = pipeline("ATCGATCG")
-        
+
         Note:
             - The pipeline includes all necessary components for training and inference
             - Model weights, tokenizer, and datasets are automatically loaded
@@ -108,17 +108,17 @@ class PipelineHub:
     def push(self, pipeline, **kwargs):
         """
         Push a pipeline to the hub (not yet implemented).
-        
+
         This method is intended to upload custom pipelines to the OmniGenome hub
         for sharing and distribution. Currently not implemented.
-        
+
         Args:
             pipeline (Pipeline): Pipeline instance to upload to the hub.
             **kwargs: Additional keyword arguments for the upload process.
-        
+
         Raises:
             NotImplementedError: This method has not been implemented yet.
-        
+
         Note:
             Future implementation will support:
             - Pipeline metadata and documentation

{omnigenome-0.3.0a0.dist-info → omnigenome-0.3.1a0.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: omnigenome
-Version: 0.3.0a0
+Version: 0.3.1a0
 Summary: OmniGenome: A comprehensive toolkit for genome analysis.
-Home-page: https://github.com/yangheng95/omnigenome
+Home-page: https://github.com/yangheng95/OmniGenBench
 Author: Yang, Heng
 Author-email: hy345@exeter.ac.uk
-License: MIT
+License: Apache-2.0
 Platform: Windows
 Platform: Linux
 Platform: Mac OS-X

omnigenome-0.3.1a0.dist-info/RECORD

@@ -0,0 +1,78 @@
+omnigenome/__init__.py,sha256=2tXjLkxTWA1Akx9iks04X-JZckhVmkIEPDO5wKTucF8,9897
+omnigenome/auto/__init__.py,sha256=UhcuYy43WsR7IowjajlcGwNVFFFDaufl8KqtNDmVqz0,97
+omnigenome/auto/auto_bench/__init__.py,sha256=M2roe3FdlmRLeXs9cOH00KrccLrazkDvlYGSg_N9upo,410
+omnigenome/auto/auto_bench/auto_bench.py,sha256=BdCzS-KF_Eos22TGlNdTtLFXlNt0Hd6yYpfvb1TawjE,20997
+omnigenome/auto/auto_bench/auto_bench_cli.py,sha256=B3iJiTKuAc6dkEu2h9ApGFpJJwS0I2zwxXtZ6bWfarM,7608
+omnigenome/auto/auto_bench/auto_bench_config.py,sha256=2mw6VFcWCSR6dJVAGDejlwmK_VmAZgqMvYlqznl5Ck8,7723
+omnigenome/auto/auto_bench/config_check.py,sha256=5RYOOOC-CqvU-46-3uSK6vspLtPSVxdZsFMnNa-3rj0,1086
+omnigenome/auto/auto_train/__init__.py,sha256=JClK_1E1_YVAy2rNzQewYzYxvLanqm71-swdXAx8uZs,447
+omnigenome/auto/auto_train/auto_train.py,sha256=af5ca6SGyxn8apIxwU0vKPoAC0mKDP2CFqN9w1N_a2M,17506
+omnigenome/auto/auto_train/auto_train_cli.py,sha256=vSjQ1t3hfe4HEvIWVB7V6cmYf-47_obKZGHWrk_LWDc,7298
+omnigenome/auto/bench_hub/__init__.py,sha256=JryopzWvewnBtN_EZKNEDKvIsc6x0wCsntNFyCGhpmU,395
+omnigenome/auto/bench_hub/bench_hub.py,sha256=eTxcVrKQdb-tdgt4CZDmD7zsUxMdw6McOeDAuaDiQZc,740
+omnigenome/cli/__init__.py,sha256=sLM_HMGX4lK8LKvIsIBmQUAbZKih6bfYoHmqQFKfGBM,445
+omnigenome/cli/omnigenome_cli.py,sha256=fvpxWqowa7IFSU097EXrhChYcMN4yekGS9UA5nsbpz4,4386
+omnigenome/cli/commands/__init__.py,sha256=nnD9NFBNHGYhUt7nI5y4iuylIn2JOdvn6iEhlDJjhes,435
+omnigenome/cli/commands/base.py,sha256=KU_lhhZpjCMRAK0LZz_txV3R9ZfzCAo_k3u44cBztMk,2858
+omnigenome/cli/commands/bench/__init__.py,sha256=dAVl47_QKktT5DpHjv0VMY18vlmxkNMSXbfIWZ1l69k,440
+omnigenome/cli/commands/bench/bench_cli.py,sha256=N4mkhg2MRo3beAWmUDJe2NsB5vL3hquxs8fBN-c9Z-A,7523
+omnigenome/cli/commands/rna/__init__.py,sha256=rUyJljDj9JGcn83iyRSB2qC2BAXkgsbb24SWsimOFVE,434
+omnigenome/cli/commands/rna/rna_design.py,sha256=Vb9jhh4Aj8RlUsBSHirQY5supkmMYzaXNIbs32Jjsyo,6408
+omnigenome/src/__init__.py,sha256=MtntWq77RoL1K6iUQQlVcwgfDZIrykvjcpP4O4_7jgM,412
+omnigenome/src/abc/__init__.py,sha256=4E5Ba2Fwf9VlxmjwZ50kku-YPGU00JZPgAcNuesaG3g,424
+omnigenome/src/abc/abstract_dataset.py,sha256=YEHMwqohAPozmmbVemzA7CoA2hKyvrkW1wIB1msEQqA,24254
+omnigenome/src/abc/abstract_metric.py,sha256=nRISSO93i1L9Q-TDL0ZnhtKAXgLRKVlzL6oKHknFU-4,4326
+omnigenome/src/abc/abstract_model.py,sha256=t1XqLqs7VLJ4I9Tzu0chWYyFr3_ElaHk5vzQK5JGa7E,28639
+omnigenome/src/abc/abstract_tokenizer.py,sha256=5z5dhL2qSswTa5W7Gdn7u8q7sC8cBfv2JuJf3G-F8Gw,9888
+omnigenome/src/dataset/__init__.py,sha256=2Lz3xfGaiP5hl2Pf1eW0eenpzrDk3zDyyi63CXbC4hE,628
+omnigenome/src/dataset/omni_dataset.py,sha256=dFsDraF3x9N-JIsxbAyPiDhY74BIdWn2pg0A_bV8iuc,17609
+omnigenome/src/lora/__init__.py,sha256=EncdIW5iV7LWh8JndQqoXIDTZgHWAIGaeNUEyMa1SlU,457
+omnigenome/src/lora/lora_model.py,sha256=HX_CW_ZlwHjGWLY-wcL01_6X6fIQKS7QxDZrmdmll44,10101
+omnigenome/src/metric/__init__.py,sha256=lZr6uiL44G8ujmCz98wTH_anHRv9QUdO3tUiBHriZXA,543
+omnigenome/src/metric/classification_metric.py,sha256=9AEBqtwga6cojFcS1lP_i-LGkbmn3QLAD7JGFz2Z6bY,8030
+omnigenome/src/metric/metric.py,sha256=lAn7brhugv-gOEnE3SatnhczjWDgV8JTLfWxJU-regc,7724
+omnigenome/src/metric/ranking_metric.py,sha256=iQZd7DIHIiNqykQJPNPVVjmGlrV-6nSEeKIh5o2XUt4,5670
+omnigenome/src/metric/regression_metric.py,sha256=hfUPD6TnrfrQ_wpW5Lyk6t6xdHyMWhJ0rthsk3MXJkw,7585
+omnigenome/src/misc/__init__.py,sha256=Dpa-uCQdwKVKkprqy26Np71mRobcWglCjgtITjU6yw0,63
+omnigenome/src/misc/utils.py,sha256=WHoXcRpwliV1-9YO5ZfttvJNzUGib77uHS6oNVUnVjo,17108
+omnigenome/src/model/__init__.py,sha256=vu1vJVYp8FR9BgF7X2msKkwMfa6jbzsfAsUHduTB21w,621
+omnigenome/src/model/module_utils.py,sha256=dmiORa835Jg6cGS24h8e1ZrwfB9_tGiz30IbwUagdaw,9158
+omnigenome/src/model/augmentation/__init__.py,sha256=Q1uTFVJjlDV_nJZ9YP44gq6LSolz9b8_6gJ0Iz0RtAc,395
+omnigenome/src/model/augmentation/model.py,sha256=rA-NZGzydqvpZuHy4fq4xVJcFA97rjb6NcoV-Leeaqg,8174
+omnigenome/src/model/classification/__init__.py,sha256=T1pW6HLdjUywf4-mN9d4ERRWPiZsGpDqsbalFPtyVCc,399
+omnigenome/src/model/classification/model.py,sha256=wAets3HAF_T66LbBmdoEutKMYAwaIvWvMffDgGhnUbU,25022
+omnigenome/src/model/embedding/__init__.py,sha256=Q6UqgzCEOujfAvYKcHnYhCa6kMIzFFFIa_5Ut8iHQgg,394
+omnigenome/src/model/embedding/model.py,sha256=JJIjQTy50U8fVzeeXbgvUdJv_W59dF-f0gZD6qB8ha8,10140
+omnigenome/src/model/mlm/__init__.py,sha256=PqKckKLXhvkJr8dLkSpKTwFYsclGv51nhXBKjI55oYw,406
+omnigenome/src/model/mlm/model.py,sha256=rFYjn_QYFcREqHzSGO8GsbdUGGMzjOkAcooa-P9SaQ8,6435
+omnigenome/src/model/regression/__init__.py,sha256=9_PEGxaiJrwPXvzOf6jGx6Wl1x4UQlOsCGUwNYPUDbc,395
+omnigenome/src/model/regression/model.py,sha256=lXLg1Z0B7jzXHRkt8F1sP3KAitfSIAvhe8EAOFiUMFI,27591
+omnigenome/src/model/regression/resnet.py,sha256=Xvpssyo3LmmPMJYHwdqKHU0x9F39dllkKY94aI9mHO0,16861
+omnigenome/src/model/rna_design/__init__.py,sha256=cqC0Ap954sBDOe3RI8nVlYahx_gIg0nqwoBg8CRQ62E,395
+omnigenome/src/model/rna_design/model.py,sha256=kDDM0BHpoFN9nlGxNWrjTjsFWn7E6CPYjfAfkJyLxGY,16939
+omnigenome/src/model/seq2seq/__init__.py,sha256=38YtCYxAQRytOsW98G8cqgCXB6mmzrSGPKs1DbwzZ40,405
+omnigenome/src/model/seq2seq/model.py,sha256=UC7j691BSbr6He3kCYwO_93V4RLWLt3fQOCQnnwJwgQ,1695
+omnigenome/src/tokenizer/__init__.py,sha256=zYUgX-FJ-fw0GNJuuW8ovo9kflDmGDd8Z0F3AMDFXF4,556
+omnigenome/src/tokenizer/bpe_tokenizer.py,sha256=_g1x3jJ3wzGgDu3_y2pW-KghYllgbiqoJfjMUF3sNTE,7646
+omnigenome/src/tokenizer/kmers_tokenizer.py,sha256=KpPA5_MSP-Wvbp2aeRGD67al6xS1unhbreIQOio-1U4,9155
+omnigenome/src/tokenizer/single_nucleotide_tokenizer.py,sha256=alwWeXuvGvzGflsyzm_V0AelAbdfMs79FGSo4pL5roo,9710
+omnigenome/src/trainer/__init__.py,sha256=adib_MJlED-EXXkNCt9MhV1U9mPPoOrLReA-dxhgdT0,453
+omnigenome/src/trainer/accelerate_trainer.py,sha256=u0gU1MRLjEcj3zPAkDztjxU1aNWDA_XTl6k_Wk3esIs,28377
+omnigenome/src/trainer/hf_trainer.py,sha256=eRw0v21lBZW1gTi-5zmagLuR0A1X7OOb0bZlmzROcMI,2591
+omnigenome/src/trainer/trainer.py,sha256=wyHJcb8IhrIrSW9dE7uK5MU_EL0_LRHJBP65z7RW9gA,21333
+omnigenome/utility/__init__.py,sha256=UvgBH3hsW2JoXfGG6dHJeQLHVF7rXdzK39wGCoJOEKI,101
+omnigenome/utility/ensemble.py,sha256=z9opb_9H213OeeNn4VJbKQfXVK_Kzig3mNDIjviG1oQ,13141
+omnigenome/utility/hub_utils.py,sha256=iYxt1iAKW2OTsQ0rYxMixRiarwIxjYzCQtaDyijFnWw,20269
+omnigenome/utility/dataset_hub/__init__.py,sha256=86rjBJixstpSiTbtprf0RnaC1V5lykh2Bs2cnZG9j3s,433
+omnigenome/utility/dataset_hub/dataset_hub.py,sha256=aTPfk5Owoa5OtSGbFPM34WmZ3Oy9x8ZrILQgF6VXI3g,6960
+omnigenome/utility/model_hub/__init__.py,sha256=Y5AcnzrtX9zPVbsAZy-6kLPJef-eddcPtZRAe8N7BOE,391
+omnigenome/utility/model_hub/model_hub.py,sha256=0K0XOQvPLiscHt0LRphF7Gja6MXHDgBARbdQzr1G8mI,8574
+omnigenome/utility/pipeline_hub/__init__.py,sha256=lz9kdc_arVwqDENvt_dN0h8fAhBeTRyG6LQRQrQAjGE,394
+omnigenome/utility/pipeline_hub/pipeline.py,sha256=Ft56dolrLJWSLBj7jba8Fka3yCwtBso2Vx_Nt17ZB7A,19756
+omnigenome/utility/pipeline_hub/pipeline_hub.py,sha256=bt2QLg4cld8QT2fbMZXJKL0vE3ReuNWHsqhLgiwc6HI,5268
+omnigenome-0.3.1a0.dist-info/licenses/LICENSE,sha256=oQoefBV6siHctF0ET-OO3EaSZgtqGtf-wdIAmokS8iY,11560
+omnigenome-0.3.1a0.dist-info/METADATA,sha256=LA0FxjRSjsEhsXvOV3noKYAis1t4_JY-wqTDjV9Fszo,10315
+omnigenome-0.3.1a0.dist-info/WHEEL,sha256=lTU6B6eIfYoiQJTZNc-fyaR6BpL6ehTzU3xGYxn2n8k,91
+omnigenome-0.3.1a0.dist-info/entry_points.txt,sha256=uu40UgMPxY65ASdRbrhkwH94r7CIYgyG_iDBmqFQbD8,84
+omnigenome-0.3.1a0.dist-info/top_level.txt,sha256=LVFxm_WPaxjj9KnAqdW94W4D4lbOk30gdsaKlJiSzTo,11
+omnigenome-0.3.1a0.dist-info/RECORD,,

{omnigenome-0.3.0a0.dist-info → omnigenome-0.3.1a0.dist-info}/top_level.txt

@@ -1,2 +1 @@
 omnigenome
-tests

omnigenome-0.3.0a0.dist-info/RECORD

@@ -1,85 +0,0 @@
-omnigenome/__init__.py,sha256=rG1SRLhIMfh9IbKkpDjoaa99jx67AItyNmW9hmQ6WF0,10719
-omnigenome/auto/__init__.py,sha256=UhcuYy43WsR7IowjajlcGwNVFFFDaufl8KqtNDmVqz0,97
-omnigenome/auto/auto_bench/__init__.py,sha256=o0sPxaZM_KP5lRgidFUySr12OWguqB6PlL9ZhvWV1DM,411
-omnigenome/auto/auto_bench/auto_bench.py,sha256=nprUgDGLLh4OIG9Qys6Aing1j8n_aw3ndSmx4PzAYN4,20781
-omnigenome/auto/auto_bench/auto_bench_cli.py,sha256=B3iJiTKuAc6dkEu2h9ApGFpJJwS0I2zwxXtZ6bWfarM,7608
-omnigenome/auto/auto_bench/auto_bench_config.py,sha256=2mw6VFcWCSR6dJVAGDejlwmK_VmAZgqMvYlqznl5Ck8,7723
-omnigenome/auto/auto_bench/config_check.py,sha256=5RYOOOC-CqvU-46-3uSK6vspLtPSVxdZsFMnNa-3rj0,1086
-omnigenome/auto/auto_train/__init__.py,sha256=piAuS6ry7obkTthpbBvn5u2kqqhtrTwiGsrWIPqE4w0,448
-omnigenome/auto/auto_train/auto_train.py,sha256=ne2G9oOMsqYysDxpOQbrp-v29-aDqtuAu4fo_HG4D2A,17563
-omnigenome/auto/auto_train/auto_train_cli.py,sha256=vSjQ1t3hfe4HEvIWVB7V6cmYf-47_obKZGHWrk_LWDc,7298
-omnigenome/auto/bench_hub/__init__.py,sha256=lbqmvd01gyyaijag-cg_MqjIlKcXfDskf-vLaWKpxBM,396
-omnigenome/auto/bench_hub/bench_hub.py,sha256=CsnONzpcDw2HWNszCa_Ak4zUpIqKhV72cENkG0qoB0U,744
-omnigenome/cli/__init__.py,sha256=xDO_D_enpEDCkpOqIcgIBn_nA7Na1x3AIHFfw42w_XU,446
-omnigenome/cli/omnigenome_cli.py,sha256=fvpxWqowa7IFSU097EXrhChYcMN4yekGS9UA5nsbpz4,4386
-omnigenome/cli/commands/__init__.py,sha256=vKd5VEfonNnNc6k77q2lGyfpyA12Lgl9cI0soMU24Ns,436
-omnigenome/cli/commands/base.py,sha256=cziPHmbzHyBlQ1t-SbDt3k1Mwkb9i6cba8i-MCaoRWw,2931
-omnigenome/cli/commands/bench/__init__.py,sha256=BnoQ23hFXEkKy8GtNVQbynvGyKNkvVF8UFDSmSprSAI,441
-omnigenome/cli/commands/bench/bench_cli.py,sha256=5tpPpV_pIBC4_oUoD2jz9GlMjEHR7f-zbThlIYkWrwU,7625
-omnigenome/cli/commands/rna/__init__.py,sha256=hLyxZjMFFSGU8wuSEaxvWxM2plLbCGoI9B-sMcrxjvY,435
-omnigenome/cli/commands/rna/rna_design.py,sha256=JQGaCMMTq45mTAxFXylFQ4gfpLWb9mvciTRGtapDpu8,6519
-omnigenome/src/__init__.py,sha256=gciGhCbdgcNEVoyquqnWubNmN1X-Ir53dHT2cAgOZUk,413
-omnigenome/src/abc/__init__.py,sha256=RdVIA2WOyGbt9aTdMWXDZIG3I_6M49BV_WP8ti887LM,425
-omnigenome/src/abc/abstract_dataset.py,sha256=jZFRVnAmif4gwGvhi2uYApLPYyYTz6k-RENGeWizrfU,23816
-omnigenome/src/abc/abstract_metric.py,sha256=bR5mBnEiDAzBbzd2kF8aYV59Kipej2wZ8QlZsPzFP7o,4353
-omnigenome/src/abc/abstract_model.py,sha256=E_YuhScqBi8Qt_-wEbTtP0c_dxv0oz7fe7NfyFNszwk,28670
-omnigenome/src/abc/abstract_tokenizer.py,sha256=tfiYddutKIuUZiQJ3ujiakehWINiGOYbrKV-tUwtF5U,9894
-omnigenome/src/dataset/__init__.py,sha256=2Lz3xfGaiP5hl2Pf1eW0eenpzrDk3zDyyi63CXbC4hE,628
-omnigenome/src/dataset/omni_dataset.py,sha256=1ryp9TZu7Josv3ua_8GZJbA6BOOIeQ3Ty_kBtj9FgRc,17633
-omnigenome/src/lora/__init__.py,sha256=VRNwSjziZywM4bRegcho4y1zGNF-kvBgxYXyATSgRL0,458
-omnigenome/src/lora/lora_model.py,sha256=cFE2SW-KW9G64tu8mb94ymwtZsg4N0Ykmj3p8V6fh1k,10293
-omnigenome/src/metric/__init__.py,sha256=lZr6uiL44G8ujmCz98wTH_anHRv9QUdO3tUiBHriZXA,543
-omnigenome/src/metric/classification_metric.py,sha256=ndv2MPx6xv0k0CaHVQoeWyUW5HkMCqqZ0okeUUsXtgs,8109
-omnigenome/src/metric/metric.py,sha256=mDd-8huMv9PiyWSaVWiIqNIaXQC5yI-zc_5WOTXWAxY,7912
-omnigenome/src/metric/ranking_metric.py,sha256=DTyNyhleDPDPEyg5HlDjlUpLS5uYne17SdDUejpXmCs,5826
-omnigenome/src/metric/regression_metric.py,sha256=J_XOZ1jXSdqzkOgw4adHA-YLA4A_QcGlW8g0lgIm9xs,7753
-omnigenome/src/misc/__init__.py,sha256=Dpa-uCQdwKVKkprqy26Np71mRobcWglCjgtITjU6yw0,63
-omnigenome/src/misc/utils.py,sha256=8b7FHp0OlyIbmbINOEgHa9nlhKz5qZ92x1tfAy7S0ko,15296
-omnigenome/src/model/__init__.py,sha256=vu1vJVYp8FR9BgF7X2msKkwMfa6jbzsfAsUHduTB21w,621
-omnigenome/src/model/module_utils.py,sha256=rPJJfAcA4C8KumxSBJRCrCRxUSrwiRvLdbilIYIPS5U,9286
-omnigenome/src/model/augmentation/__init__.py,sha256=JEZ1rszRUq7NBzwyu02eyNb_TTph2K3lXnXOCbHTtJc,396
-omnigenome/src/model/augmentation/model.py,sha256=VHfi4z1LX5mDKrjHqg_B7kCvykc-E-YZd-TMSSn8yV0,8318
-omnigenome/src/model/classification/__init__.py,sha256=6LxPh0ROdvzxMRLyLiksuX32H3F72vIbm1N3VCPnz4A,400
-omnigenome/src/model/classification/model.py,sha256=_XPiVhoF-7QD_VV9shG5c95F_XD6t8E-czg3Eb2xDdQ,25184
-omnigenome/src/model/embedding/__init__.py,sha256=pxrepPcVIp5ZmkEC5M3vRnmBJJTB1qXII5Zot_WSA3k,395
-omnigenome/src/model/embedding/model.py,sha256=H3XyIJ-HxgYDPFqnfd1XsWO3JYV5DnDAbMqgz6oe3g0,10355
-omnigenome/src/model/mlm/__init__.py,sha256=_rVEdL3nec_7hze2nTG0jgoupDJYMyl8EVcb02ZNwRs,407
-omnigenome/src/model/mlm/model.py,sha256=RaUiX66Kzinn6vE1Rp23paJSOJP78EpxS0a9QJinQn0,6547
-omnigenome/src/model/regression/__init__.py,sha256=Qdd4ctbc6jqTJDxHLe5MzSA3eDvW4vdypJm28bMQkco,396
-omnigenome/src/model/regression/model.py,sha256=sgFqZ00J_gmeP9eRt1JYlbNN_KZhWLP1m4bEKKzV1Z8,28177
-omnigenome/src/model/regression/resnet.py,sha256=YgzUAhGdXG_pAmvjQOpEjjzwxtm7sOb-a4et0CPJ09Y,17093
-omnigenome/src/model/rna_design/__init__.py,sha256=jHAhyxuJScz1h1HY1UfZ3_fSVmwJOwsSACQkTItAl38,396
-omnigenome/src/model/rna_design/model.py,sha256=_4RQtlmLPCpMCDXWweV_FOiWPNN-ZrjceWcnw9Gphsc,15826
-omnigenome/src/model/seq2seq/__init__.py,sha256=OAi4RVSwCbFOIvEwQZCDTImBOFrLkHs1JXwipL_4fqs,406
-omnigenome/src/model/seq2seq/model.py,sha256=-dGUjg7uRmnbR4rPH_lF8SgpR-U5lCoVJm4oNqzCOGg,1715
-omnigenome/src/tokenizer/__init__.py,sha256=zYUgX-FJ-fw0GNJuuW8ovo9kflDmGDd8Z0F3AMDFXF4,556
-omnigenome/src/tokenizer/bpe_tokenizer.py,sha256=5_qIuTYOWkhZH4O1jRf-hm4C130SjyVQP6avQkAkUr4,7898
-omnigenome/src/tokenizer/kmers_tokenizer.py,sha256=KqyoY3xxllhl2Ij3YZk_zuW16dtH96I0hU5OMvO-EtA,9359
-omnigenome/src/tokenizer/single_nucleotide_tokenizer.py,sha256=MAIeTtqQUDn6LYbYMy8RTzIU6S40rM5IE-imyM2MgFE,9794
-omnigenome/src/trainer/__init__.py,sha256=adib_MJlED-EXXkNCt9MhV1U9mPPoOrLReA-dxhgdT0,453
-omnigenome/src/trainer/accelerate_trainer.py,sha256=d5xtBdxtNWFyPYtodGkmnUi8t9ex3qlD4YFNOy3hvaY,28393
-omnigenome/src/trainer/hf_trainer.py,sha256=FdWU7g7iH0s-pmbTDOqYBwVMr6TKSKGUyrcfhum39Nk,2631
-omnigenome/src/trainer/trainer.py,sha256=NByvYdcazND_c9Ot2RSxoFjOV-Wc6kReu099BZbk13A,21179
-omnigenome/utility/__init__.py,sha256=UvgBH3hsW2JoXfGG6dHJeQLHVF7rXdzK39wGCoJOEKI,101
-omnigenome/utility/ensemble.py,sha256=2xSDvGULKJwE5LfLWfnNjsWo2DFf_TFmvqyhrYFlC90,13413
-omnigenome/utility/hub_utils.py,sha256=yJF5RVICFbWy9JQU2P0lM3NXumu7HxNLCjpTKAudZf4,20313
-omnigenome/utility/dataset_hub/__init__.py,sha256=6OTdqTWgKkuPQRBCGycpS1BboBoyT8rF3jY1EBSSAmE,434
-omnigenome/utility/dataset_hub/dataset_hub.py,sha256=OW0XE27nCbuVD18UatFwi1w4UEfKxnv77R61D7bd0Vg,7008
-omnigenome/utility/model_hub/__init__.py,sha256=N0xf5urzb6MxR8g-xF1CTzX0OFpHjngfETk6cmn92sc,392
-omnigenome/utility/model_hub/model_hub.py,sha256=kgyjrU9qUb_pflIKqOQOUrk3zlF5pM8JazBxJyiBTck,8792
-omnigenome/utility/pipeline_hub/__init__.py,sha256=rm7k6GDXyrYGQyLO3ZFpYLnjAYf6s8xmJuOPypDNQ-g,395
-omnigenome/utility/pipeline_hub/pipeline.py,sha256=F_pDC_JKJF3b8OZtqzKzl99Q1FLMRQdBaGURi8CjZzg,20121
-omnigenome/utility/pipeline_hub/pipeline_hub.py,sha256=9HB5xZTr8HZtsuC6MrWWNbR4cg_5BW0CVXKQk2AwcWA,5384
-omnigenome-0.3.0a0.dist-info/licenses/LICENSE,sha256=oQoefBV6siHctF0ET-OO3EaSZgtqGtf-wdIAmokS8iY,11560
-tests/__init__.py,sha256=MsAPLRxLTpyXAhwM2gnJ4ibJT6h5-SvyFd7gglSfZ2c,270
-tests/conftest.py,sha256=YNK66YqdtjofE65R59JJ2aiq24a3ltQ1ISSdf4Uqvlg,4344
-tests/test_dataset_patterns.py,sha256=x0pv09jOircm2fzbZ1xseCitZCSEftoOvVKv-3O_BJ4,11020
-tests/test_examples_syntax.py,sha256=0ERqLxOoi05zGZqkKKaAoHkhWggxyXGd7h2HVVd2Wtc,3277
-tests/test_model_loading.py,sha256=H5Ug1jNns74_CzL_j5fzqm_eFke4VlQF9HEmAV733eY,7145
-tests/test_rna_functions.py,sha256=f5RsT0n1dWv8YCuHkAaXzUjrn3nLqNoe3CIyGfMDYNY,10066
-tests/test_training_patterns.py,sha256=ouAP-tDlAbUR2EmHjqDcsMnfOyp3Y4s7rfftzxZPF0I,10979
-omnigenome-0.3.0a0.dist-info/METADATA,sha256=gQmzq0zgIiL7Lbl8qvMqraVDPqRu74C_WTDF9LODX0M,10306
-omnigenome-0.3.0a0.dist-info/WHEEL,sha256=lTU6B6eIfYoiQJTZNc-fyaR6BpL6ehTzU3xGYxn2n8k,91
-omnigenome-0.3.0a0.dist-info/entry_points.txt,sha256=uu40UgMPxY65ASdRbrhkwH94r7CIYgyG_iDBmqFQbD8,84
-omnigenome-0.3.0a0.dist-info/top_level.txt,sha256=m8gQveMmM9nKDt36SOZTsagU7jEtZq7seCOwmDws-Lw,17
-omnigenome-0.3.0a0.dist-info/RECORD,,

tests/__init__.py

@@ -1,9 +0,0 @@
-"""
-OmniGenBench test suite.
-
-This test suite validates functionality based on examples in the examples/ directory.
-Tests are designed to be fast and avoid heavy dependencies while ensuring
-code patterns and interfaces work correctly.
-"""
-
-__version__ = "0.1.0"