Update README.md

README.md

@@ -13,4 +13,61 @@ license: apache-2.0
 widget:
 - text: "Mixed Martial Arts joinbodi, Ultimate Fighting Championship, UFC don decide say dem go enta back di octagon on Saturday, 9 May, for Jacksonville, Florida."
 ---
-Model description
+
+# Model description
+**mbert-base-uncased-ner-pcm**  is a model based on the fine-tuned Multilingual BERT base uncased model, previously fine-tuned for Named Entity Recognition using 10 high-resourced languages. It has been trained to recognize four types of entities:
+- dates & time (DATE)
+- Location (LOC)
+- Organizations (ORG)
+- Person (PER)
+
+# Intended Use
+- Intended to be used for research purposes concerning Named Entity Recognition for African Languages.
+- Not intended for practical purposes.
+
+# Training Data
+This model was fine-tuned on the Nigerian Pidgin corpus **(pcm)** of the [MasakhaNER](https://github.com/masakhane-io/masakhane-ner) dataset. However, we thresholded the number of entity groups per sentence in this dataset to 10 entity groups.
+
+# Training procedure
+This model was trained on a single NVIDIA P5000 from [Paperspace](https://www.paperspace.com)
+#### Hyperparameters
+- **Learning Rate:** 5e-5
+- **Batch Size:** 32
+- **Maximum Sequence Length:** 164
+- **Epochs:** 30
+
+# Evaluation Data
+We evaluated this model on the test split of the Swahili corpus **(pcm)** present in the [MasakhaNER](https://github.com/masakhane-io/masakhane-ner) with no thresholding.
+
+# Metrics
+- Precision
+- Recall
+- F1-score
+
+# Limitations
+- The size of the pre-trained language model prevents its usage in anything other than research.
+- Lack of analysis concerning the bias and fairness in these models may make them dangerous if deployed into production system.
+- The train data is a less populated version of the original dataset in terms of entity groups per sentence. Therefore, this can negatively impact the performance.
+
+# Caveats and Recommendations
+- The topics in the dataset corpus are centered around **News**. Future training could be done with a more diverse corpus.
+
+# Results
+Model Name| Precision | Recall | F1-score
+-|-|-|-
+**mbert-base-uncased-ner-pcm**| 90.38 | 82.44 | 86.23
+
+# Usage
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+from transformers import pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("arnolfokam/mbert-base-uncased-ner-pcm")
+model = AutoModelForTokenClassification.from_pretrained("mbert-base-uncased-ner-pcm")
+
+nlp = pipeline("ner", model=model, tokenizer=tokenizer)
+example = "Mixed Martial Arts joinbodi, Ultimate Fighting Championship, UFC don decide say dem go enta back di octagon on Saturday, 9 May, for Jacksonville, Florida."
+
+ner_results = nlp(example)
+print(ner_results)
+```