Updated API

README.md

@@ -7,4 +7,65 @@ sdk: docker
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# Random Baseline Model for Climate Disinformation Classification
+
+## Model Description
+
+This is a random baseline model for the Frugal AI Challenge 2024, specifically for the text classification task of identifying climate disinformation. The model serves as a performance floor, randomly assigning labels to text inputs without any learning.
+
+### Intended Use
+
+- **Primary intended uses**: Baseline comparison for climate disinformation classification models
+- **Primary intended users**: Researchers and developers participating in the Frugal AI Challenge
+- **Out-of-scope use cases**: Not intended for production use or real-world classification tasks
+
+## Training Data
+
+The model uses the QuotaClimat/frugalaichallenge-text-train dataset:
+- Size: ~6000 examples
+- Split: 80% train, 20% test
+- 8 categories of climate disinformation claims
+
+### Labels
+0. No relevant claim detected
+1. Global warming is not happening
+2. Not caused by humans
+3. Not bad or beneficial
+4. Solutions harmful/unnecessary
+5. Science is unreliable
+6. Proponents are biased
+7. Fossil fuels are needed
+
+## Performance
+
+### Metrics
+- **Accuracy**: ~12.5% (random chance with 8 classes)
+- **Environmental Impact**:
+  - Emissions tracked in gCO2eq
+  - Energy consumption tracked in Wh
+
+### Model Architecture
+The model implements a random choice between the 8 possible labels, serving as the simplest possible baseline.
+
+## Environmental Impact
+
+Environmental impact is tracked using CodeCarbon, measuring:
+- Carbon emissions during inference
+- Energy consumption during inference
+
+This tracking helps establish a baseline for the environmental impact of model deployment and inference.
+
+## Limitations
+- Makes completely random predictions
+- No learning or pattern recognition
+- No consideration of input text
+- Serves only as a baseline reference
+- Not suitable for any real-world applications
+
+## Ethical Considerations
+
+- Dataset contains sensitive topics related to climate disinformation
+- Model makes random predictions and should not be used for actual classification
+- Environmental impact is tracked to promote awareness of AI's carbon footprint
+```

requirements.txt

@@ -4,4 +4,6 @@ codecarbon>=2.3.1
 datasets>=2.14.0
 scikit-learn>=1.0.2
 pydantic>=1.10.0
-python-dotenv>=1.0.0
+python-dotenv>=1.0.0
+gradio>=4.0.0
+requests>=2.31.0

tasks/audio.py

@@ -4,20 +4,27 @@ from .utils.emissions import get_space_info
 
 router = APIRouter()
 
-@router.post("/audio", tags=["Audio Task"])
+DESCRIPTION = "Random Baseline"
+
+@router.post("/audio", tags=["Audio Task"],
+             description=DESCRIPTION)
 async def evaluate_audio(request: AudioEvaluationRequest):
     """
-    Placeholder for audio task evaluation.
+    Evaluate audio classification.
+    
+    Current Model: Random Baseline
+    - Makes random predictions
+    - Used as a baseline for comparison
     """
     username, space_url = get_space_info()
     return {
         "message": "Audio evaluation endpoint not yet implemented",
         "username": username,
         "space_url": space_url,
+        "model_description": DESCRIPTION,
         "received_config": {
             "dataset_name": request.dataset_name,
             "test_size": request.test_size,
-            "test_seed": request.test_seed,
-            "model_description": request.model_description
+            "test_seed": request.test_seed
         }
     } 

tasks/image.py

@@ -4,20 +4,27 @@ from .utils.emissions import get_space_info
 
 router = APIRouter()
 
-@router.post("/image", tags=["Image Task"])
+DESCRIPTION = "Random Baseline"
+
+@router.post("/image", tags=["Image Task"],
+             description=DESCRIPTION)
 async def evaluate_image(request: ImageEvaluationRequest):
     """
-    Placeholder for image task evaluation.
+    Evaluate image classification.
+    
+    Current Model: Random Baseline
+    - Makes random predictions
+    - Used as a baseline for comparison
     """
     username, space_url = get_space_info()
     return {
         "message": "Image evaluation endpoint not yet implemented",
         "username": username,
         "space_url": space_url,
+        "model_description": DESCRIPTION,
         "received_config": {
             "dataset_name": request.dataset_name,
             "test_size": request.test_size,
-            "test_seed": request.test_seed,
-            "model_description": request.model_description
+            "test_seed": request.test_seed
         }
     } 

tasks/text.py

@@ -9,10 +9,17 @@ from .utils.emissions import tracker, clean_emissions_data, get_space_info
 
 router = APIRouter()
 
-@router.post("/text", tags=["Text Task"])
+DESCRIPTION = "Random Baseline"
+
+@router.post("/text", tags=["Text Task"], 
+             description=DESCRIPTION)
 async def evaluate_text(request: TextEvaluationRequest):
     """
-    Evaluate a text classification model for climate disinformation detection.
+    Evaluate text classification for climate disinformation detection.
+    
+    Current Model: Random Baseline
+    - Makes random predictions from the label space (0-7)
+    - Used as a baseline for comparison
     """
     # Get space info
     username, space_url = get_space_info()
@@ -42,10 +49,20 @@ async def evaluate_text(request: TextEvaluationRequest):
     # Start tracking emissions
     tracker.start()
     tracker.start_task("inference")
+
+    #--------------------------------------------------------------------------------------------
+    # YOUR MODEL INFERENCE CODE HERE
+    # Update the code below to replace the random baseline by your model inference within the inference pass where the energy consumption and emissions are tracked.
+    #--------------------------------------------------------------------------------------------   
     
     # Make random predictions (placeholder for actual model inference)
     true_labels = test_dataset["label"]
     predictions = [random.randint(0, 7) for _ in range(len(true_labels))]
+
+    #--------------------------------------------------------------------------------------------
+    # YOUR MODEL INFERENCE STOPS HERE
+    #--------------------------------------------------------------------------------------------   
+
     
     # Stop tracking emissions
     emissions_data = tracker.stop_task()
@@ -58,7 +75,7 @@ async def evaluate_text(request: TextEvaluationRequest):
         "username": username,
         "space_url": space_url,
         "submission_timestamp": datetime.now().isoformat(),
-        "model_description": request.model_description,
+        "model_description": DESCRIPTION,
         "accuracy": float(accuracy),
         "energy_consumed_wh": emissions_data.energy_consumed * 1000,
         "emissions_gco2eq": emissions_data.emissions * 1000,

tasks/utils/evaluation.py

@@ -4,7 +4,6 @@ from pydantic import BaseModel, Field
 class BaseEvaluationRequest(BaseModel):
     test_size: float = Field(0.2, ge=0.0, le=1.0, description="Size of the test split (between 0 and 1)")
     test_seed: int = Field(42, ge=0, description="Random seed for reproducibility")
-    model_description: Optional[str] = Field("No description provided", description="Description of the model being evaluated")
 
 class TextEvaluationRequest(BaseEvaluationRequest):
     dataset_name: str = Field("QuotaClimat/frugalaichallenge-text-train",