Upload folder using huggingface_hub

LICENSE

@@ -0,0 +1,176 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND

README.md

@@ -1,3 +1,63 @@
----
-license: apache-2.0
----
+---
+language: san
+license: apache-2.0
+tags:
+- dependency-parsing
+- nested-compound-type-identification
+- lstm
+- nlp
+- sanskrit
+- pytorch
+---
+
+# DepNeCTI-LSTM: Dependency-based Nested Compound Type Identification for Sanskrit
+
+This repository contains the **DepNeCTI-LSTM** model checkpoint and configuration files trained for nested compound type identification in Sanskrit using a dependency-based LSTM encoder.
+
+---
+
+## Model Details
+
+- **Model type:** LSTM-based dependency parser  
+- **Task:** Nested Compound Type Identification (NeCTI) in Sanskrit  
+- **Architecture:** LSTM encoder with word, POS, and character embeddings  
+- **Trained on:** DepNeCTI dataset (from [Sandhan et al., 2023](https://arxiv.org/abs/2310.09501))  
+- **Pretrained embeddings used:** FastText embeddings (cc.NeCTIS.300.txt)  
+- **Framework:** PyTorch 1.13.0  
+- **CUDA version:** 11.7  
+
+---
+
+## Files
+
+- `domain_san.pt` — Pretrained model state for the Domain-SAN model.
+
+- `domain_san.arg.json` — JSON file containing model hyperparameters and configuration settings.  
+
+- `README.md` — Instructions for setup, usage, and reproduction of results. 
+
+- `requirements.txt` — List of Python dependencies required to run the model.
+
+- `LICENSE` — Apache License 2.0 — grants broad usage rights with conditions for attribution and inclusion of the license when redistributing.
+
+---
+
+## Usage
+
+This model and arguments(json format) were obtained after running the training script. To reproduce the model in accordance to your needs refer to the [original paper](http://arxiv.org/abs/2310.09501)
+
+
+# Paper
+```
+@misc{sandhan2023depnecti,
+      title={DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit}, 
+      author={Jivnesh Sandhan and Yaswanth Narsupalli and Sreevatsa Muppirala and Sriram Krishnan and Pavankumar Satuluri and Amba Kulkarni and Pawan Goyal},
+      year={2023},
+      eprint={2310.09501},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
+}
+```
+Original paper [DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit](http://arxiv.org/abs/2310.09501)
+
+Github Repository of [DepNeCTI](https://github.com/yaswanth-iitkgp/DepNeCTI)

domain_san.arg.json

@@ -0,0 +1,60 @@
+{
+    "dataset": "ud",
+    "domain": "san",
+    "rnn_mode": "LSTM",
+    "gating": false,
+    "num_gates": 0,
+    "num_epochs": 100,
+    "batch_size": 128,
+    "hidden_size": 512,
+    "arc_space": 512,
+    "arc_tag_space": 128,
+    "num_layers": 2,
+    "num_filters": 100,
+    "kernel_size": 3,
+    "use_pos": true,
+    "use_char": true,
+    "pos_dim": 100,
+    "char_dim": 100,
+    "initializer": "xavier",
+    "opt": "adam",
+    "momentum": 0.9,
+    "betas": [
+        0.9,
+        0.9
+    ],
+    "learning_rate": 0.002,
+    "decay_rate": 0.5,
+    "schedule": 6,
+    "clip": 5.0,
+    "gamma": 0.0,
+    "epsilon": 1e-06,
+    "p_rnn": [
+        0.1,
+        0.1
+    ],
+    "p_in": 0.1,
+    "p_out": 0.1,
+    "arc_decode": "mst",
+    "unk_replace": 0.0,
+    "punct_set": [
+        ".",
+        "``",
+        ":",
+        ","
+    ],
+    "word_embedding": "fasttext",
+    "word_path": "data/cc.NeCTIS.300.txt",
+    "freeze_word_embeddings": false,
+    "freeze_sequence_taggers": false,
+    "char_embedding": "random",
+    "pos_embedding": "random",
+    "char_path": null,
+    "pos_path": null,
+    "set_num_training_samples": null,
+    "model_path": "saved_models/Coarse_NeCTIS",
+    "load_path": null,
+    "load_sequence_taggers_paths": null,
+    "strict": false,
+    "eval_mode": false
+}

domain_san.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71032d8f2b36a8d236db2bc53cfda4ac16082374b3fa846cb43e019769afab90
+size 270618416

requirements.txt

@@ -0,0 +1,33 @@
+backports.functools-lru-cache==1.6.5
+certifi==2023.5.7
+click==8.1.3
+cycler==0.11.0
+docopt==0.6.2
+fontstyle==1.0.1.2
+fonttools==4.38.0
+gensim==3.8.1
+importlib-metadata==6.7.0
+indic-transliteration==2.3.44
+kiwisolver==1.4.5
+matplotlib==3.5.3
+mkl-fft==1.3.1
+mkl-random==1.2.2
+mkl-service==2.4.0
+pandas==1.3.5
+pipreqs==0.4.13
+pybind11==2.13.6
+pyparsing==3.1.4
+python-dateutil==2.8.2
+pytz==2023.3
+regex==2023.6.3
+roman==4.1
+scipy==1.7.3
+seaborn==0.12.2
+smart-open==6.3.0
+toml==0.10.2
+torch==1.13.0
+torchaudio==0.13.0
+torchvision==0.14.0
+typer==0.9.0
+yarg==0.1.10
+zipp==3.15.0