Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,12 @@
+# Virtual environments
+.venv/
+venv/
+env/
+
+# Python junk
+__pycache__/
+*.pyc
+
+# OS files
+.DS_Store
+Thumbs.db

README.md

@@ -1,3 +1,30 @@
----
-license: apache-2.0
----
+---
+language: luo
+license: apache-2.0
+tags:
+- pos-tagging
+- token-classification
+- dholuo
+- afroxlmr
+- masakhane
+datasets:
+- kencorpus
+model_name: Dholuo POS Tagger (AfroXLM-R)
+---
+
+# Dholuo POS Tagger (AfroXLM-R)
+
+This model is a fine-tuned version of `masakhane/luo-pos-tagger-afroxlmr`
+trained on KenCorpus POS-tagged Dholuo data.
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+
+model = AutoModelForTokenClassification.from_pretrained(
+    "Omballa/dholuo-pos-afroxlmr-finetuned"
+)
+tokenizer = AutoTokenizer.from_pretrained(
+    "Omballa/dholuo-pos-afroxlmr-finetuned"
+)

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "X",
+    "1": "ADJ",
+    "2": "ADP",
+    "3": "ADV",
+    "4": "AUX",
+    "5": "CCONJ",
+    "6": "DET",
+    "7": "INTJ",
+    "8": "NOUN",
+    "9": "NUM",
+    "10": "PART",
+    "11": "PRON",
+    "12": "PROPN",
+    "13": "PUNCT",
+    "14": "SCONJ",
+    "15": "SYM",
+    "16": "VERB"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "ADJ": 1,
+    "ADP": 2,
+    "ADV": 3,
+    "AUX": 4,
+    "CCONJ": 5,
+    "DET": 6,
+    "INTJ": 7,
+    "NOUN": 8,
+    "NUM": 9,
+    "PART": 10,
+    "PRON": 11,
+    "PROPN": 12,
+    "PUNCT": 13,
+    "SCONJ": 14,
+    "SYM": 15,
+    "VERB": 16,
+    "X": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce05451562b2b5604e4ee1aa9dbeac168e58814f6a35f725d808fc9e38bfe7d2
+size 2235481556

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63c7a5faf7f3257542d756311f64572a52913c2845c4a3849529e1ef87f8eef
+size 17082832

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:894c9e55e44de957e6d58186e55ad49f985f6932ab9e7b400ff9b0d9b349e48b
+size 5841