Upload folder using huggingface_hub

README.md

@@ -0,0 +1,105 @@
+---
+license: cc-by-sa-4.0
+language:
+  - te
+tags:
+  - dependency-parsing
+  - combo
+  - universal-dependencies
+datasets:
+  - universal_dependencies
+model-name: Combo Nlp Xlm Roberta Base Telugu Mtg Ud2.17
+pipeline_tag: token-classification
+---
+
+# COMBO-NLP Model for Telugu
+
+## Model Description
+
+This is a Telugu-language model based on [COMBO-NLP](https://gitlab.clarin-pl.eu/syntactic-tools/combo-nlp), an open-source natural language preprocessing system. It performs:
+
+- sentence segmentation (via [LAMBO](https://gitlab.clarin-pl.eu/syntactic-tools/lambo))
+- tokenisation (via [LAMBO](https://gitlab.clarin-pl.eu/syntactic-tools/lambo))
+- part-of-speech tagging
+- morphological analysis
+- lemmatisation
+- dependency parsing
+
+The Telugu model uses ``FacebookAI/xlm-roberta-base`` as its base encoder and is trained on [UD_Telugu-MTG](https://github.com/UniversalDependencies/UD_Telugu-MTG) (UD v2.17).
+
+## Evaluation
+
+Evaluation was performed on the UD_Telugu-MTG test split using the standard [CoNLL 2018 eval script](https://universaldependencies.org/conll18/conll18_ud_eval.py).
+
+Two evaluation rows are reported:
+- **Full-text (F1)**: raw text is segmented by [LAMBO](https://gitlab.clarin-pl.eu/syntactic-tools/lambo), then parsed and compared against gold — measures end-to-end pipeline performance including segmentation quality.
+- **Aligned accuracy**: accuracy on correctly segmented (aligned) tokens — measures parsing quality on tokens that were correctly identified by the segmenter.
+
+### Morphosyntactic Tagging
+
+| Metric | Tokens | Sentences | Words | UPOS | XPOS | UFeats | AllTags | Lemmas |
+| ------ | ------ | --------- | ----- | ---- | ---- | ------ | ------- | ------ |
+| Full-text (F1) | 99.79 | 96.60 | 99.79 | 94.94 | 94.80 | 98.96 | 94.66 | 99.79 |
+| Aligned accuracy | 0.00 | 0.00 | 0.00 | 95.14 | 95.00 | 99.17 | 94.86 | 100.00 |
+
+### Dependency Parsing
+
+| Metric | UAS | LAS | CLAS | MLAS | BLEX |
+| ------ | --- | --- | ---- | ---- | ---- |
+| Full-text (F1) | 91.61 | 84.13 | 80.76 | 77.33 | 80.76 |
+| Aligned accuracy | 91.81 | 84.31 | 80.92 | 77.48 | 80.92 |
+
+
+## Usage
+
+Install the library from PyPI (assuming you have a virtual environment created):
+
+```bash
+pip install combo-nlp
+```
+
+Install the Lambo segmenter - only needed when passing raw text strings to COMBO:
+
+```bash
+pip install --index-url https://pypi.clarin-pl.eu/ lambo
+```
+
+```python
+from combo import COMBO
+
+# Load a pre-trained model with corresponding Lambo segmenter
+nlp = COMBO("Telugu")
+
+# Parse raw text (handles sentence splitting + tokenization)
+result = nlp("వేగవంతమైన గోధుమ రంగు నక్క సోమరి కుక్క మీదుగా దూకుతుంది.")
+
+# Inspect results
+for sentence in result:
+    for token in sentence:
+        print(f"{token.form:<15} {token.lemma:<15} {token.upos:<8} head={token.head}  {token.deprel}")
+```
+
+Refer to the COMBO-NLP documentation for installation and usage instructions:
+
+- [https://gitlab.clarin-pl.eu/syntactic-tools/combo-nlp](https://gitlab.clarin-pl.eu/syntactic-tools/combo-nlp)
+- [https://gitlab.clarin-pl.eu/syntactic-tools/lambo](https://gitlab.clarin-pl.eu/syntactic-tools/lambo)
+
+## Citation
+
+<!--
+```bibtex
+@misc{combo_nlp_2026,
+  title = {COMBO-NLP Models Trained on UD v2.17},
+  author = {Ulewicz, Michał and Jabłońska, Maja and Klimaszewski, Mateusz and Przybyła, Piotr and Pszenny, Łukasz and Rybak, Piotr and Wiącek, Martyna and Wróblewska, Alina},
+  year = {2026},
+  howpublished = {\url{https://huggingface.co/collections/clarin-pl/combo-ud-217-models}}
+}
+```
+-->
+
+## Resources
+
+- COMBO-NLP: [https://gitlab.clarin-pl.eu/syntactic-tools/combo-nlp](https://gitlab.clarin-pl.eu/syntactic-tools/combo-nlp)
+- LAMBO: [https://gitlab.clarin-pl.eu/syntactic-tools/lambo](https://gitlab.clarin-pl.eu/syntactic-tools/lambo)
+- UD_Telugu-MTG: [https://github.com/UniversalDependencies/UD_Telugu-MTG](https://github.com/UniversalDependencies/UD_Telugu-MTG)
+

config.json

@@ -0,0 +1,66 @@
+{
+  "model": {
+    "use_lora": false,
+    "lora_r": 64,
+    "lora_alpha": 128,
+    "lora_dropout": 0.05,
+    "lora_target_modules": [
+      "query",
+      "key",
+      "value",
+      "output.dense"
+    ],
+    "arc_hidden_dim": 256,
+    "rel_hidden_dim": 128,
+    "char_embed_dim": 300,
+    "max_char_len": 50,
+    "dropout": 0.1,
+    "lemma_input_proj_dim": 32,
+    "lemma_input_proj_dropout": 0.25,
+    "lemma_cnn_filters": [
+      256,
+      256,
+      256
+    ],
+    "lemma_cnn_kernel_sizes": [
+      3,
+      3,
+      3,
+      1
+    ],
+    "lemma_cnn_dilations": [
+      1,
+      2,
+      4,
+      1
+    ],
+    "lemma_cnn_paddings": [
+      1,
+      2,
+      4,
+      0
+    ],
+    "morpho_weight": 1.0,
+    "feats_weight": 3.0,
+    "arc_weight": 1.0,
+    "rel_weight": 1.0,
+    "lemma_weight": 1.5,
+    "use_uncertainty_weighting": false,
+    "morpho_to_lemma_proj_dim": 64,
+    "lemma_beam_width": 5,
+    "use_lemma_beam_search": true,
+    "use_morpho_constraints": true,
+    "base_model": "FacebookAI/xlm-roberta-base",
+    "num_upos": 16,
+    "num_xpos": 16,
+    "feat_vocab_sizes": {
+      "NumType": 3
+    },
+    "feat_categories": [
+      "NumType"
+    ],
+    "num_deprels": 41,
+    "char_vocab_size": 90
+  },
+  "max_length": 512
+}

encoders/char_vocab.json

@@ -0,0 +1,95 @@
+{
+  "char_to_id": {
+    "<PAD>": 0,
+    "<UNK>": 1,
+    "<SOS>": 2,
+    "<EOS>": 3,
+    "\u0c1a": 4,
+    "\u0c42": 5,
+    "\u0c38": 6,
+    "\u0c47": 7,
+    "\u0c30": 8,
+    "\u0c3e": 9,
+    "\u0c05": 10,
+    "\u0c02": 11,
+    "\u0c21": 12,
+    "\u0c40": 13,
+    "?": 14,
+    "\u0c0e": 15,
+    "\u0c15": 16,
+    "\u0c4d": 17,
+    "\u0c3f": 18,
+    "\u0c35": 19,
+    "\u0c46": 20,
+    "\u0c33": 21,
+    "\u0c24": 22,
+    "\u0c41": 23,
+    "\u0c28": 24,
+    "\u0c2a": 25,
+    "\u0c4b": 26,
+    "\u0c2f": 27,
+    "\u0c2e": 28,
+    "\u0c1f": 29,
+    "\u0c26": 30,
+    "\u0c08": 31,
+    "\u0c2c": 32,
+    "\u0c27": 33,
+    "\u0c07": 34,
+    "!": 35,
+    "\u0c32": 36,
+    "\u0c37": 37,
+    "\u0c23": 38,
+    "\u0c09": 39,
+    ".": 40,
+    ",": 41,
+    "\u0c17": 42,
+    "\u0c06": 43,
+    "\u0c0f": 44,
+    "\u0c39": 45,
+    "\u0c36": 46,
+    "\u0c1c": 47,
+    "\u0c0a": 48,
+    "\u0c4a": 49,
+    "\u0c2d": 50,
+    "\u0c20": 51,
+    "\u0c12": 52,
+    "\u0c2b": 53,
+    "\"": 54,
+    "\u0c48": 55,
+    "\u0c16": 56,
+    "\u0c43": 57,
+    "(": 58,
+    ")": 59,
+    "\u0c25": 60,
+    "\u0c14": 61,
+    "\u0c1d": 62,
+    "\u0c10": 63,
+    "\u0c4c": 64,
+    "-": 65,
+    "r": 66,
+    "a": 67,
+    "m": 68,
+    "u": 69,
+    "c": 70,
+    "e": 71,
+    "s": 72,
+    "i": 73,
+    "n": 74,
+    "p": 75,
+    "T": 76,
+    "k": 77,
+    "o": 78,
+    "N": 79,
+    "D": 80,
+    "l": 81,
+    "\u0c13": 82,
+    ":": 83,
+    ";": 84,
+    "\u0c1e": 85,
+    "\u0c18": 86,
+    "w": 87,
+    "E": 88,
+    "g": 89
+  },
+  "max_len": 50
+}

encoders/deprel_encoder.json

@@ -0,0 +1,45 @@
+{
+  "label_to_id": {
+    "<PAD>": 0,
+    "<UNK>": 1,
+    "root": 2,
+    "discourse": 3,
+    "punct": 4,
+    "obl": 5,
+    "obl:tmod": 6,
+    "case": 7,
+    "nsubj": 8,
+    "det": 9,
+    "advcl": 10,
+    "nmod:poss": 11,
+    "obj": 12,
+    "compound:svc": 13,
+    "nmod": 14,
+    "nummod": 15,
+    "advmod": 16,
+    "conj": 17,
+    "nsubj:nc": 18,
+    "cc": 19,
+    "compound": 20,
+    "amod": 21,
+    "vocative": 22,
+    "parataxis": 23,
+    "obl:cmp": 24,
+    "compound:lvc": 25,
+    "ccomp": 26,
+    "mark": 27,
+    "iobj": 28,
+    "xcomp": 29,
+    "acl:relcl": 30,
+    "csubj": 31,
+    "acl": 32,
+    "flat": 33,
+    "orphan": 34,
+    "advcl:cond": 35,
+    "compound:redup": 36,
+    "dislocated": 37,
+    "obl:cau": 38,
+    "list": 39,
+    "nmod:tmod": 40
+  }
+}

encoders/morpho_encoder.json

@@ -0,0 +1,126 @@
+{
+  "upos": {
+    "label_to_id": {
+      "<PAD>": 0,
+      "<UNK>": 1,
+      "VERB": 2,
+      "PART": 3,
+      "PUNCT": 4,
+      "NOUN": 5,
+      "PRON": 6,
+      "PROPN": 7,
+      "ADP": 8,
+      "DET": 9,
+      "NUM": 10,
+      "ADV": 11,
+      "CCONJ": 12,
+      "ADJ": 13,
+      "INTJ": 14,
+      "SCONJ": 15
+    }
+  },
+  "xpos": {
+    "label_to_id": {
+      "<PAD>": 0,
+      "<UNK>": 1,
+      "VERB": 2,
+      "PART": 3,
+      "PUNCT": 4,
+      "NOUN": 5,
+      "PRON": 6,
+      "PROPN": 7,
+      "ADP": 8,
+      "DET": 9,
+      "NUM": 10,
+      "ADV": 11,
+      "CCONJ": 12,
+      "ADJ": 13,
+      "INTJ": 14,
+      "SCONJ": 15
+    }
+  },
+  "feat_categories": [
+    "NumType"
+  ],
+  "feats": {
+    "NumType": {
+      "label_to_id": {
+        "<PAD>": 0,
+        "<UNK>": 1,
+        "Card": 2
+      }
+    }
+  },
+  "valid_feat_vectors": {
+    "2": [
+      [
+        0
+      ]
+    ],
+    "3": [
+      [
+        0
+      ]
+    ],
+    "4": [
+      [
+        0
+      ]
+    ],
+    "5": [
+      [
+        0
+      ]
+    ],
+    "6": [
+      [
+        0
+      ]
+    ],
+    "7": [
+      [
+        0
+      ]
+    ],
+    "8": [
+      [
+        0
+      ]
+    ],
+    "9": [
+      [
+        0
+      ]
+    ],
+    "10": [
+      [
+        2
+      ]
+    ],
+    "11": [
+      [
+        0
+      ]
+    ],
+    "12": [
+      [
+        0
+      ]
+    ],
+    "13": [
+      [
+        0
+      ]
+    ],
+    "14": [
+      [
+        0
+      ]
+    ],
+    "15": [
+      [
+        0
+      ]
+    ]
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8d08c81263bfa552bad8b54fa3220b6f823e5eb5310417c03e26fe3f986ad2f
+size 1129825247