Update

.gitignore

@@ -0,0 +1 @@
+train

README.md

@@ -1,50 +1,14 @@
 ---
 title: classicier
-datasets:
--  
+emoji: ⏳
+colorFrom: blue
+colorTo: pink
 tags:
 - evaluate
 - metric
-description: "TODO: add a description here"
+description: Classify if a given sentence is in Classical Arabic or Not
 sdk: gradio
 sdk_version: 3.19.1
 app_file: app.py
 pinned: false
----
-
-# Metric Card for classicier
-
-***Module Card Instructions:*** *Fill out the following subsections. Feel free to take a look at existing metric cards if you'd like examples.*
-
-## Metric Description
-*Give a brief overview of this metric, including what task(s) it is usually used for, if any.*
-
-## How to Use
-*Give general statement of how to use the metric*
-
-*Provide simplest possible example for using the metric*
-
-### Inputs
-*List all input arguments in the format below*
-- **input_field** *(type): Definition of input, with explanation if necessary. State any default value(s).*
-
-### Output Values
-
-*Explain what this metric outputs and provide an example of what the metric output looks like. Modules should return a dictionary with one or multiple key-value pairs, e.g. {"bleu" : 6.02}*
-
-*State the range of possible values that the metric's output can take, as well as what in that range is considered good. For example: "This metric can take on any value between 0 and 100, inclusive. Higher scores are better."*
-
-#### Values from Popular Papers
-*Give examples, preferrably with links to leaderboards or publications, to papers that have reported this metric, along with the values they have reported.*
-
-### Examples
-*Give code examples of the metric being used. Try to include examples that clear up any potential ambiguity left from the metric description above. If possible, provide a range of examples that show both typical and atypical results, as well as examples where a variety of input parameters are passed.*
-
-## Limitations and Bias
-*Note any known limitations or biases that the metric has, with links and references if possible.*
-
-## Citation
-*Cite the source where this metric was introduced.*
-
-## Further References
-*Add any useful further references.*
+---

classicier.py

@@ -1,95 +1,48 @@
-# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-"""TODO: Add a description here."""
-
 import evaluate
 import datasets
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
 
-
-# TODO: Add BibTeX citation
-_CITATION = """\
-@InProceedings{huggingface:module,
-title = {A great new module},
-authors={huggingface, Inc.},
-year={2020}
-}
-"""
-
-# TODO: Add description of the module here
-_DESCRIPTION = """\
-This new module is designed to solve this great ML task and is crafted with a lot of care.
-"""
-
-
-# TODO: Add description of the arguments of the module here
-_KWARGS_DESCRIPTION = """
-Calculates how good are predictions given some references, using certain scores
-Args:
-    predictions: list of predictions to score. Each predictions
-        should be a string with tokens separated by spaces.
-    references: list of reference for each prediction. Each
-        reference should be a string with tokens separated by spaces.
-Returns:
-    accuracy: description of the first score,
-    another_score: description of the second score,
-Examples:
-    Examples should be written in doctest format, and should illustrate how
-    to use the function.
-
-    >>> my_new_module = evaluate.load("my_new_module")
-    >>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
-    >>> print(results)
-    {'accuracy': 1.0}
-"""
-
-# TODO: Define external resources urls if needed
-BAD_WORDS_URL = "http://url/to/external/resource/bad_words.txt"
-
-
-@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
-class classicier(evaluate.Metric):
-    """TODO: Short description of my evaluation module."""
-
+class Classicier(evaluate.Measurement):
+    
     def _info(self):
-        # TODO: Specifies the evaluate.EvaluationModuleInfo object
-        return evaluate.MetricInfo(
-            # This is the description that will appear on the modules page.
-            module_type="metric",
-            description=_DESCRIPTION,
-            citation=_CITATION,
-            inputs_description=_KWARGS_DESCRIPTION,
-            # This defines the format of each prediction and reference
-            features=datasets.Features({
-                'predictions': datasets.Value('int64'),
-                'references': datasets.Value('int64'),
-            }),
-            # Homepage of the module for documentation
-            homepage="http://module.homepage",
-            # Additional links to the codebase or references
-            codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
-            reference_urls=["http://path.to.reference.url/new_module"]
+        return evaluate.MeasurementInfo(
+            description="",
+            citation="",
+            inputs_description="",
+            features=datasets.Features(
+                {
+                    "texts": datasets.Value("string", id="sequence"),
+                }
+            ),
+            reference_urls=[],
         )
-
-    def _download_and_prepare(self, dl_manager):
-        """Optional: download external resources useful to compute the scores"""
-        # TODO: Download external resources if needed
-        pass
-
-    def _compute(self, predictions, references):
-        """Returns the scores"""
-        # TODO: Compute the different scores of the module
-        accuracy = sum(i == j for i, j in zip(predictions, references)) / len(predictions)
-        return {
-            "accuracy": accuracy,
-        }
+    
+    def _download_and_prepare(self, dl_manager, device=None):
+        if device is None:
+            device = "cuda" if torch.cuda.is_available() else "cpu"
+        
+        # Load the tokenizer and model from the specified repository
+        self.tokenizer = AutoTokenizer.from_pretrained("AbdulmohsenA/classicier")
+        self.model = AutoModelForSequenceClassification.from_pretrained("AbdulmohsenA/classicier")
+        
+        self.model.to(device)
+        self.device = device
+
+    def _compute(self, texts, temperature=2):
+        device = self.device
+        
+        inputs = self.tokenizer(
+            texts, 
+            return_tensors="pt", 
+            truncation=True, 
+            padding='max_length', 
+            max_length=128
+        ).to(device)
+        
+        with torch.no_grad():
+            output = self.model(**inputs)
+            prediction = torch.softmax(output.logits / temperature, dim=-1)
+            classical_prob = prediction[:, 1].detach().cpu().numpy()
+
+        return {"classical_score": classical_prob}

requirements.txt

@@ -1 +1,4 @@
-git+https://github.com/huggingface/evaluate@main
+evaluate
+transformers
+torch
+datasets