Update language model

README.md

@@ -19,58 +19,40 @@ model-index:
 - name: LusakaLang-MultiTask
   results:
   - task:
-      name: Language Identification
       type: text-classification
+      name: Language Identification
     dataset:
       name: LusakaLang Language Data
       type: lusakalang
       split: test
     metrics:
-    - name: accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.97
-    - name: f1_macro
-      type: f1
+      name: accuracy
+    - type: f1
       value: 0.96
-
-  - task:
-      name: Sentiment Analysis
-      type: text-classification
-    dataset:
-      name: LusakaLang Sentiment Data
-      type: lusakalang
-      split: test
-    metrics:
-    - name: accuracy
-      type: accuracy
+      name: f1_macro
+    - type: accuracy
       value: 0.9322
-    - name: f1_macro
-      type: f1
+      name: accuracy
+    - type: f1
       value: 0.9216
-    - name: f1_negative
-      type: f1
+      name: f1_macro
+    - type: f1
       value: 0.8649
-    - name: f1_neutral
-      type: f1
+      name: f1_negative
+    - type: f1
       value: 0.95
-    - name: f1_positive
-      type: f1
+      name: f1_neutral
+    - type: f1
       value: 0.95
-
-  - task:
-      name: Topic Classification
-      type: text-classification
-    dataset:
-      name: LusakaLang Topic Data
-      type: lusakalang
-      split: test
-    metrics:
-    - name: accuracy
-      type: accuracy
+      name: f1_positive
+    - type: accuracy
       value: 0.91
-    - name: f1_macro
-      type: f1
-      value: 0.90
+      name: accuracy
+    - type: f1
+      value: 0.9
+      name: f1_macro
 ---
 
 

config.json

@@ -1,22 +1,43 @@
 {
-    "model_type": "bert-multitask",
-    "base_model": "google-bert/bert-base-multilingual-cased",
-    "language_labels": {
-        "0": "bemba",
-        "1": "nyanja",
-        "2": "english",
-        "3": "unknown"
-    },
-    "sentiment_labels": {
-        "0": "negative",
-        "1": "neutral",
-        "2": "positive"
-    },
-    "topic_labels": {
-        "0": "customer_support",
-        "1": "driver_behaviour",
-        "2": "others",
-        "3": "payment_issues"
-    },
-    "hidden_size": 768
-}
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "bemba",
+    "1": "nyanja",
+    "2": "english",
+    "3": "unknown"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bemba": 0,
+    "english": 2,
+    "nyanja": 1,
+    "unknown": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b43d0fc5dfb79c55fd1dd2f6ae890fc93cc6970dff58f34dad36ec9f67b445
-size 711469000
+oid sha256:52d7a4c94dc09a3259ebbcad5e182564fabc7b30bcc7f9eb0e5bf3f526c12b7d
+size 711449608