fundacionctic
/

oracle-dermat

@@ -35,11 +35,11 @@ It takes as input four features:
 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 - **Developed by:** [Fundacion CTIC](https://www.fundacionctic.org)
-- **Funded by [optional]:** [SATEC](https://www.satec.es)
 - **Model type:** Fine-tuned LM Encoder
 - **Language(s) (NLP):** Spanish
 - **License:** CC-BY-NC
-- **Finetuned from model [optional]:** [bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es)
 ### Model Sources [optional]
@@ -58,24 +58,17 @@ We DO NOT recommend to fine-tune this model. It is already meant to be a downstr
 This model can be directly used for classifying dermatological text data in Spanish EHRs.
-### Downstream Use [optional]
 The model can be integrated into healthcare applications for automatic classification of dermatological conditions from patient records.
-[More Information Needed]
 ### Out-of-Scope Use
 The model is not suitable for non-medical text classification tasks or for texts in languages other than Spanish.
-[More Information Needed]
 ## Bias, Risks, and Limitations
 This model is fine-tuned on a specific dataset and may not generalize well to other types of medical texts or conditions. Users should be cautious of biases in the training data that could affect the model's performance.
-[More Information Needed]
 ### Recommendations
 <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
@@ -108,29 +101,25 @@ outputs = model(input_ids, attention_mask=attention_mask)
 ### Training Data
 The model was fine-tuned on the DermatES dataset from Fundación CTIC, which contains Spanish dermatological EHRs.
-[More Information Needed]
 ### Training Procedure
 The training used two NVIDIA GPUs (11gb and 49gb)
-#### Preprocessing [optional]
 Lowercased, anonymized and accents removed texts
 #### Training Hyperparameters
 - **Training regime:** fp32
-#### Speeds, Sizes, Times [optional]
     Epochs: 9
     Batch size: 64
     Learning rate: 0.0001
-[More Information Needed]
 ## Evaluation
@@ -142,8 +131,6 @@ Lowercased, anonymized and accents removed texts
 The evaluation was performed on 0.2 of the [DermatES](https://huggingface.co/datasets/fundacionctic/DermatES) dataset.
-[More Information Needed]
 #### Factors
 <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
@@ -180,7 +167,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 - **Compute Region:** [More Information Needed]
 - **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
 ### Model Architecture and Objective
@@ -193,6 +180,7 @@ The model is based on the [RoBERTa](https://huggingface.co/FacebookAI/roberta-ba
 #### Hardware
 Two NVIDIA GPUs were used for the fine-tuning process.
 #### Software
 The fine-tuning was performed using the 🤗 Transformers library.
@@ -203,8 +191,6 @@ The fine-tuning was performed using the 🤗 Transformers library.
 **BibTeX:** Coming soon
-[More Information Needed]
 **APA:**
 [More Information Needed]
@@ -217,10 +203,11 @@ The fine-tuning was performed using the 🤗 Transformers library.
 [More Information Needed]
-## Model Card Authors [optional]
 Leon-Paul Schaub Torre, Pelayo Quiros and Helena Garcia-Mieres
 ## Model Card Contact
-leon.schaub@fundacionctic.org

 This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 - **Developed by:** [Fundacion CTIC](https://www.fundacionctic.org)
+- **Funded by:** [SATEC](https://www.satec.es)
 - **Model type:** Fine-tuned LM Encoder
 - **Language(s) (NLP):** Spanish
 - **License:** CC-BY-NC
+- **Finetuned from model:** [bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es)
 ### Model Sources [optional]
 This model can be directly used for classifying dermatological text data in Spanish EHRs.
+### Downstream Use
 The model can be integrated into healthcare applications for automatic classification of dermatological conditions from patient records.
 ### Out-of-Scope Use
 The model is not suitable for non-medical text classification tasks or for texts in languages other than Spanish.
 ## Bias, Risks, and Limitations
 This model is fine-tuned on a specific dataset and may not generalize well to other types of medical texts or conditions. Users should be cautious of biases in the training data that could affect the model's performance.
 ### Recommendations
 <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 ### Training Data
 The model was fine-tuned on the DermatES dataset from Fundación CTIC, which contains Spanish dermatological EHRs.
 ### Training Procedure
 The training used two NVIDIA GPUs (11gb and 49gb)
+#### Preprocessing
 Lowercased, anonymized and accents removed texts
 #### Training Hyperparameters
 - **Training regime:** fp32
+#### Speeds, Sizes, Times
     Epochs: 9
     Batch size: 64
     Learning rate: 0.0001
 ## Evaluation
 The evaluation was performed on 0.2 of the [DermatES](https://huggingface.co/datasets/fundacionctic/DermatES) dataset.
 #### Factors
 <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
 - **Compute Region:** [More Information Needed]
 - **Carbon Emitted:** [More Information Needed]
+## Technical Specifications
 ### Model Architecture and Objective
 #### Hardware
 Two NVIDIA GPUs were used for the fine-tuning process.
 #### Software
 The fine-tuning was performed using the 🤗 Transformers library.
 **BibTeX:** Coming soon
 **APA:**
 [More Information Needed]
 [More Information Needed]
+## Model Card Authors
 Leon-Paul Schaub Torre, Pelayo Quiros and Helena Garcia-Mieres
 ## Model Card Contact
+leon.schaub@fundacionctic.org
+pelayo.quiros@fundacionctic.org